Communication can promote coordination in cooperative Multi-Agent Reinforcement Learning (MARL). Nowadays, existing works mainly focus on improving the communication efficiency of agents, neglecting that real-world communication is much more challenging as there may exist noise or potential attackers. Thus the robustness of the communication-based policies becomes an emergent and severe issue that needs more exploration. In this paper, we posit that the ego system

Here ego system means the multi-agent communication system itself. We use the word ego to distinguish it from the generated adversaries.

trained with auxiliary adversaries may handle this limitation and propose an adaptable method of Multi-Agent Auxiliary Adversaries Generation for robust Communication, dubbed MA3C, to obtain a robust communication-based policy. In specific, we introduce a novel message-attacking approach that models the learning of the auxiliary attacker as a cooperative problem under a shared goal to minimize the coordination ability of the ego system, with which every information channel may suffer from distinct message attacks. Furthermore, as naive adversarial training may impede the generalization ability of the ego system, we design an attacker population generation approach based on evolutionary learning. Finally, the ego system is paired with an attacker population and then alternatively trained against the continuously evolving attackers to improve its robustness, meaning that both the ego system and the attackers are adaptable. Extensive experiments on multiple benchmarks indicate that our proposed MA3C provides comparable or better robustness and generalization ability than other baselines.

Random sample partition (RSP) is a newly developed big data representation and management model to deal with big data approximate computation problems. Academic research and practical applications have confirmed that RSP is an efficient solution for big data processing and analysis. However, a challenge for implementing RSP is determining an appropriate sample size for RSP data blocks. While a large sample size increases the burden of big data computation, a small size will lead to insufficient distribution information for RSP data blocks. To address this problem, this paper presents a novel density estimation-based method (DEM) to determine the optimal sample size for RSP data blocks. First, a theoretical sample size is calculated based on the multivariate Dvoretzky-Kiefer-Wolfowitz (DKW) inequality by using the fixed-point iteration (FPI) method. Second, a practical sample size is determined by minimizing the validation error of a kernel density estimator (KDE) constructed on RSP data blocks for an increasing sample size. Finally, a series of persuasive experiments are conducted to validate the feasibility, rationality, and effectiveness of DEM. Experimental results show that (1) the iteration function of the FPI method is convergent for calculating the theoretical sample size from the multivariate DKW inequality; (2) the KDE constructed on RSP data blocks with sample size determined by DEM can yield a good approximation of the probability density function (p.d.f.); and (3) DEM provides more accurate sample sizes than the existing sample size determination methods from the perspective of p.d.f. estimation. This demonstrates that DEM is a viable approach to deal with the sample size determination problem for big data RSP implementation.

Question Generation (QG) is the task of generating questions according to the given contexts. Most of the existing methods are based on Recurrent Neural Networks (RNNs) for generating questions with passage-level input for providing more details, which seriously suffer from such problems as gradient vanishing and ineffective information utilization. In fact, reasonably extracting useful information from a given context is more in line with our actual needs during questioning especially in the education scenario. To that end, in this paper, we propose a novel Hierarchical Answer-Aware and Context-Aware Network (HACAN) to construct a high-quality passage representation and judge the balance between the sentences and the whole passage. Specifically, a Hierarchical Passage Encoder (HPE) is proposed to construct an answer-aware and context-aware passage representation, with a strategy of utilizing multi-hop reasoning. Then, we draw inspiration from the actual human questioning process and design a Hierarchical Passage-aware Decoder (HPD) which determines when to utilize the passage information. We conduct extensive experiments on the SQuAD dataset, where the results verify the effectiveness of our model in comparison with several baselines.

Significant progress has been made in machine learning with large amounts of clean labels and static data. However, in many real-world applications, the data often changes with time and it is difficult to obtain massive clean annotations, that is, noisy labels and time series are faced simultaneously. For example, in product-buyer evaluation, each sample records the daily time behavior of users, but the long transaction period brings difficulties to analysis, and salespeople often erroneously annotate the user’s purchase behavior. Such a novel setting, to our best knowledge, has not been thoroughly studied yet, and there is still a lack of effective machine learning methods. In this paper, we present a systematic approach RTS both theoretically and empirically, consisting of two components, Noise-Tolerant Time Series Representation and Purified Oversampling Learning. Specifically, we propose reducing label noise’s destructive impact to obtain robust feature representations and potential clean samples. Then, a novel learning method based on the purified data and time series oversampling is adopted to train an unbiased model. Theoretical analysis proves that our proposal can improve the quality of the noisy data set. Empirical experiments on diverse tasks, such as the house-buyer evaluation task from real-world applications and various benchmark tasks, clearly demonstrate that our new algorithm robustly outperforms many competitive methods.

Geographically replicating objects across multiple data centers improves the performance and reliability of cloud storage systems. Maintaining consistent replicas comes with high synchronization costs, as it faces more expensive WAN transport prices and increased latency. Periodic replication is the widely used technique to reduce the synchronization costs. Periodic replication strategies in existing cloud storage systems are too static to handle traffic changes, which indicates that they are inflexible in the face of unforeseen loads, resulting in additional synchronization cost. We propose quantitative analysis models to quantify consistency and synchronization cost for periodically replicated systems, and derive the optimal synchronization period to achieve the best tradeoff between consistency and synchronization cost. Based on this, we propose a dynamic periodic synchronization method, Sync-Opt, which allows systems to set the optimal synchronization period according to the variable load in clouds to minimize the synchronization cost. Simulation results demonstrate the effectiveness of our models. Compared with the policies widely used in modern cloud storage systems, the Sync-Opt strategy significantly reduces the synchronization cost.

With the recent demonstration of quantum computers, interests in the field of reversible logic synthesis and optimization have taken a different turn. As every quantum operation is inherently reversible, there is an immense motivation for exploring reversible circuit design and optimization. When it comes to faults in circuits, the parity-preserving feature donates to the detection of permanent and temporary faults. In the context of reversible circuits, the parity-preserving property ensures that the input and output parities are equal. In this paper we suggest six parity-preserving reversible blocks (Z, F, A, T, S, and L) with improved quantum cost. The reversible blocks are synthesized using an existing synthesis method that generates a netlist of multiple-control Toffoli (MCT) gates. Various optimization rules are applied at the reversible circuit level, followed by transformation into a netlist of elementary quantum gates from the NCV library. The designs of full-adder and unsigned and signed multipliers are proposed using the functional blocks that possess parity-preserving properties. The proposed designs are compared with state-of-the-art methods and found to be better in terms of cost of realization. Average savings of 25.04%, 20.89%, 21.17%, and 51.03%, and 18.59%, 13.82%, 13.82%, and 27.65% respectively, are observed for 4-bit unsigned and 5-bit signed multipliers in terms of quantum cost, garbage output, constant input, and gate count as compared to recent works.

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for battery management systems. Deep learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series data. However, the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be improved. To address this challenge, this paper proposes a novel deep learning model, the MLP-Mixer and Mixture of Expert (MMMe) model, for RUL prediction. The MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level features. Additionally, we devise an ensemble predictor based on a Mixture-of-Experts (MoE) architecture to generate reliable RUL predictions. The experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods, providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation process. Our code and dataset are available at the website of github.

In this paper, we propose a novel warm restart technique using a new logarithmic step size for the stochastic gradient descent (SGD) approach. For smooth and non-convex functions, we establish an O\left(\frac{1}{\sqrt{T}}\right) convergence rate for the SGD. We conduct a comprehensive implementation to demonstrate the efficiency of the newly proposed step size on the FashionMinst, CIFAR10, and CIFAR100 datasets. Moreover, we compare our results with nine other existing approaches and demonstrate that the new logarithmic step size improves test accuracy by 0.9% for the CIFAR100 dataset when we utilize a convolutional neural network (CNN) model.

In crowdsourcing scenarios, we can obtain each instance’s multiple noisy labels from different crowd workers and then infer its integrated label via label aggregation. In spite of the effectiveness of label aggregation methods, there still remains a certain level of noise in the integrated labels. Thus, some noise correction methods have been proposed to reduce the impact of noise in recent years. However, to the best of our knowledge, existing methods rarely consider an instance’s information from both its features and multiple noisy labels simultaneously when identifying a noise instance. In this study, we argue that the more distinguishable an instance’s features but the noisier its multiple noisy labels, the more likely it is a noise instance. Based on this premise, we propose a label distribution similarity-based noise correction (LDSNC) method. To measure whether an instance’s features are distinguishable, we obtain each instance’s predicted label distribution by building multiple classifiers using instances’ features and their integrated labels. To measure whether an instance’s multiple noisy labels are noisy, we obtain each instance’s multiple noisy label distribution using its multiple noisy labels. Then, we use the Kullback-Leibler (KL) divergence to calculate the similarity between the predicted label distribution and multiple noisy label distribution and define the instance with the lower similarity as a noise instance. The extensive experimental results on 34 simulated and four real-world crowdsourced datasets validate the effectiveness of our method.

IP geolocation is essential for the territorial analysis of sensitive network entities, location-based services (LBS) and network fraud detection. It has important theoretical significance and application value. Measurement-based IP geolocation is a hot research topic. However, the existing IP geolocation algorithms cannot effectively utilize the distance characteristics of the delay, and the nodes’ connection relation, resulting in high geolocation error. It is challenging to obtain the mapping between delay, nodes’ connection relation, and geographical location. Based on the idea of network representation learning, we propose a representation learning model for IP nodes (IP2vec for short) and apply it to street-level IP geolocation. IP2vec model vectorizes nodes according to the connection relation and delay between nodes so that the IP vectors can reflect the distance and topological proximity between IP nodes. The steps of the street-level IP geolocation algorithm based on IP2vec model are as follows: Firstly, we measure landmarks and target IP to obtain delay and path information to construct the network topology. Secondly, we use the IP2vec model to obtain the IP vectors from the network topology. Thirdly, we train a neural network to fit the mapping relation between vectors and locations of landmarks. Finally, the vector of target IP is fed into the neural network to obtain the geographical location of target IP. The algorithm can accurately infer geographical locations of target IPs based on delay and topological proximity embedded in the IP vectors. The cross-validation experimental results on 10023 target IPs in New York, Beijing, Hong Kong, and Zhengzhou demonstrate that the proposed algorithm can achieve street-level geolocation. Compared with the existing algorithms such as Hop-Hot, IP-geolocater and SLG, the mean geolocation error of the proposed algorithm is reduced by 33%, 39%, and 51%, respectively.

Code review is a critical process in software development, contributing to the overall quality of the product by identifying errors early. A key aspect of this process is the selection of appropriate reviewers to scrutinize changes made to source code. However, in large-scale open-source projects, selecting the most suitable reviewers for a specific change can be a challenging task. To address this, we introduce the Code Context Based Reviewer Recommendation (CCB-RR), a model that leverages information from changesets to recommend the most suitable reviewers. The model takes into consideration the paths of modified files and the context derived from the changesets, including their titles and descriptions. Additionally, CCB-RR employs KeyBERT to extract the most relevant keywords and compare the semantic similarity across changesets. The model integrates the paths of modified files, keyword information, and the context of code changes to form a comprehensive picture of the changeset. We conducted extensive experiments on four open-source projects, demonstrating the effectiveness of CCB-RR. The model achieved a Top-1 accuracy of 60%, 55%, 51%, and 45% on the Android, OpenStack, QT, and LibreOffice projects respectively. For Mean Reciprocal Rank (MRR), CCB achieved 71%, 62%, 52%, and 68% on the same projects respectively, thereby highlighting its potential for practical application in code reviewer recommendation.

In Internet of Things (IoT), data sharing among different devices can improve manufacture efficiency and reduce workload, and yet make the network systems be more vulnerable to various intrusion attacks. There has been realistic demand to develop an efficient intrusion detection algorithm for connected devices. Most of existing intrusion detection methods are trained in a centralized manner and are incapable to identify new unlabeled attack types. In this paper, a distributed federated intrusion detection method is proposed, utilizing the information contained in the labeled data as the prior knowledge to discover new unlabeled attack types. Besides, the blockchain technique is introduced in the federated learning process for the consensus of the entire framework. Experimental results are provided to show that our approach can identify the malicious entities, while outperforming the existing methods in discovering new intrusion attack types.

Interpretability has drawn increasing attention in machine learning. Most works focus on post-hoc explanations rather than building a self-explaining model. So, we propose a Neural Partially Linear Additive Model (NPLAM), which automatically distinguishes insignificant, linear, and nonlinear features in neural networks. On the one hand, neural network construction fits data better than spline function under the same parameter amount; on the other hand, learnable gate design and sparsity regular-term maintain the ability of feature selection and structure discovery. We theoretically establish the generalization error bounds of the proposed method with Rademacher complexity. Experiments based on both simulations and real-world datasets verify its good performance and interpretability.

Federated Learning (FL) has emerged as a powerful technology designed for collaborative training between multiple clients and a server while maintaining data privacy of clients. To enhance the privacy in FL, Differentially Private Federated Learning (DPFL) has gradually become one of the most effective approaches. As DPFL operates in the distributed settings, there exist potential malicious adversaries who manipulate some clients and the aggregation server to produce malicious parameters and disturb the learning model. However, existing aggregation protocols for DPFL concern either the existence of some corrupted clients (Byzantines) or the corrupted server. Such protocols are limited to eliminate the effects of corrupted clients and server when both are in existence simultaneously due to the complicated threat model. In this paper, we elaborate such adversarial threat model and propose BVDFed. To our best knowledge, it is the first Byzantine-resilient and Verifiable aggregation for Differentially private FEDerated learning. In specific, we propose Differentially Private Federated Averaging algorithm (DPFA) as our primary workflow of BVDFed, which is more lightweight and easily portable than traditional DPFL algorithm. We then introduce Loss Score to indicate the trustworthiness of disguised gradients in DPFL. Based on Loss Score, we propose an aggregation rule DPLoss to eliminate faulty gradients from Byzantine clients during server aggregation while preserving the privacy of clients’ data. Additionally, we design a secure verification scheme DPVeri that are compatible with DPFA and DPLoss to support the honest clients in verifying the integrity of received aggregated results. And DPVeri also provides resistance to collusion attacks with no more than t participants for our aggregation. Theoretical analysis and experimental results demonstrate our aggregation to be feasible and effective in practice.

Recently advancements in deep learning models have significantly facilitated the development of sequential recommender systems (SRS). However, the current deep model structures are limited in their ability to learn high-quality embeddings with insufficient data. Meanwhile, highly skewed long-tail distribution is very common in recommender systems. Therefore, in this paper, we focus on enhancing the representation of tail items to improve sequential recommendation performance. Through empirical studies on benchmarks, we surprisingly observe that both the ranking performance and training procedure are greatly hindered by the poorly optimized tail item embeddings. To address this issue, we propose a sequential recommendation framework named TailRec that enables contextual information of tail item well-leveraged and greatly improves its corresponding representation. Given the characteristics of the sequential recommendation task, the surrounding interaction records of each tail item are regarded as contextual information without leveraging any additional side information. This approach allows for the mining of contextual information from cross-sequence behaviors to boost the performance of sequential recommendations. Such a light contextual filtering component is plug-and-play for a series of SRS models. To verify the effectiveness of the proposed TailRec, we conduct extensive experiments over several popular benchmark recommenders. The experimental results demonstrate that TailRec can greatly improve the recommendation results and speed up the training process. The codes of our methods have been available

See github.com/Mingyue-Cheng/TailRec website.

.

Though obstruction-free progress property is weaker than other non-blocking properties including lock-freedom and wait-freedom, it has advantages that have led to the use of obstruction-free implementations for software transactional memory (STM) and in anonymous and fault-tolerant distributed computing. However, existing work can only verify obstruction-freedom of specific data structures (e.g., STM and list-based algorithms).

In this paper, to fill this gap, we propose a program logic that can formally verify obstruction-freedom of practical implementations, as well as verify linearizability, a safety property, at the same time. We also propose informal principles to extend a logic for verifying linearizability to verifying obstruction-freedom. With this approach, the existing proof for linearizability can be reused directly to construct the proof for both linearizability and obstruction-freedom.Finally, we have successfully applied our logic to verifying a practical obstruction-free double-ended queue implementation in the first classic paper that has proposed the definition of obstruction-freedom.

The rapid development of ISAs has brought the issue of software compatibility to the forefront in the embedded field. To address this challenge, one of the promising solutions is the adoption of a multiple-ISA processor that supports multiple different ISAs. However, due to constraints in cost and performance, the architecture of a multiple-ISA processor must be carefully optimized to meet the specific requirements of embedded systems. By exploring the RISC-V and ARM Thumb ISAs, this paper proposes RVAM16, which is an optimized multiple-ISA processor microarchitecture for embedded devices based on hardware binary translation technique. The results show that, when running non-native ARM Thumb programs, RVAM16 achieves a significant speedup of over 2.73× with less area and energy consumption compared to using hardware binary translation alone, reaching more than 70% of the performance of native RISC-V programs.

Spatial crowdsourcing (SC) is a popular data collection paradigm for numerous applications. With the increment of tasks and workers in SC, heterogeneity becomes an unavoidable difficulty in task allocation. Existing researches only focus on the single-heterogeneous task allocation. However, a variety of heterogeneous objects coexist in real-world SC systems. This dramatically expands the space for searching the optimal task allocation solution, affecting the quality and efficiency of data collection. In this paper, an aggregation-based dual heterogeneous task allocation algorithm is put forth. It investigates the impact of dual heterogeneous on the task allocation problem and seeks to maximize the quality of task completion and minimize the average travel distance. This problem is first proved to be NP-hard. Then, a task aggregation method based on locations and requirements is built to reduce task failures. Meanwhile, a time-constrained shortest path planning is also developed to shorten the travel distance in a community. After that, two evolutionary task allocation schemes are presented. Finally, extensive experiments are conducted based on real-world datasets in various contexts. Compared with baseline algorithms, our proposed schemes enhance the quality of task completion by up to 25% and utilize 34% less average travel distance.

In this paper, we propose the concept of delegable zero knowledge succinct non-interactive arguments of knowledge (zk-SNARKs). The delegable zk-SNARK is parameterized by (\mu ,k,k^{\prime },k^{″}). The delegable property of zk-SNARKs allows the prover to delegate its proving ability to \mu proxies. Any k honest proxies are able to generate the correct proof for a statement, but the collusion of less than k proxies does not obtain information about the witness of the statement. We also define k^{\prime }-soundness and k^{″}-zero knowledge by taking into consider of multi-proxies.

We propose a construction of (\mu ,2t+1,t,t)- delegable zk-SNARK for the NPC language of arithmetic circuit satisfiability. Our delegable zk-SNARK stems from Groth’s zk-SNARK scheme (Groth16). We take advantage of the additive and multiplicative properties of polynomial-based secret sharing schemes to achieve delegation for zk-SNARK. Our secret sharing scheme works well with the pairing groups so that the nice succinct properties of Groth’s zk-SNARK scheme are preserved, while augmenting the delegable property and keeping soundness and zero-knowledge in the scenario of multi-proxies.

A large body of research effort has been dedicated to automated issue classification for Issue Tracking Systems (ITSs). Although the existing approaches have shown promising performance, the different design choices, including the different textual fields, feature representation methods and machine learning algorithms adopted by existing approaches, have not been comprehensively compared and analyzed. To fill this gap, we perform the first extensive study of automated issue classification on 9 state-of-the-art issue classification approaches. Our experimental results on the widely studied dataset reveal multiple practical guidelines for automated issue classification, including: (1) Training separate models for the issue titles and descriptions and then combining these two models tend to achieve better performance for issue classification; (2) Word embedding with Long Short-Term Memory (LSTM) can better extract features from the textual fields in the issues, and hence, lead to better issue classification models; (3) There exist certain terms in the textual fields that are helpful for building more discriminating classifiers between bug and non-bug issues; (4) The performance of the issue classification model is not sensitive to the choices of ML algorithms. Based on our study outcomes, we further propose an advanced issue classification approach, DEEPLABEL, which can achieve better performance compared with the existing issue classification approaches.

Deep learning has gained superior accuracy on Euclidean structure data in neural networks. As a result, non-Euclidean structure data, such as graph data, has more sophisticated structural information, which can be applied in neural networks as well to address more complex and practical problems. However, actual graph data obeys a power-law distribution, so the adjacent matrix of a graph is random and sparse. Graph processing accelerator (GPA) is designed to handle the problems above. However, graph computing only processes 1-dimensional data. In graph neural networks (GNNs), graph data is multi-dimensional. Consequently, GNNs include the execution processes of both traditional graph processing and neural network, which have irregular memory access and regular computation, respectively. To obtain more information in graph data and require better model generalization ability, the layers of GNN are deeper, so the overhead of memory access and computation is considerable. At present, GNN accelerators are designed to deal with this issue. In this paper, we conduct a systematic survey regarding the design and implementation of GNN accelerators. Specifically, we review the challenges faced by GNN accelerators, and existing related works in detail to process them. Finally, we evaluate previous works and propose future directions in this booming field.

The transformer-based semantic segmentation approaches, which divide the image into different regions by sliding windows and model the relation inside each window, have achieved outstanding success. However, since the relation modeling between windows was not the primary emphasis of previous work, it was not fully utilized. To address this issue, we propose a Graph-Segmenter, including a graph transformer and a boundary-aware attention module, which is an effective network for simultaneously modeling the more profound relation between windows in a global view and various pixels inside each window as a local one, and for substantial low-cost boundary adjustment. Specifically, we treat every window and pixel inside the window as nodes to construct graphs for both views and devise the graph transformer. The introduced boundary-aware attention module optimizes the edge information of the target objects by modeling the relationship between the pixel on the object’s edge. Extensive experiments on three widely used semantic segmentation datasets (Cityscapes, ADE-20k and PASCAL Context) demonstrate that our proposed network, a Graph Transformer with Boundary-aware Attention, can achieve state-of-the-art segmentation performance.

Wireless body area networks (WBANs) guarantee timely data processing and secure information preservation within the range of the wireless access network, which is in urgent need of a new type of security technology. However, with the speedy development of hardware, the existing security schemes can no longer meet the new requirements of anonymity and lightweight. New solutions that do not require complex calculations, such as certificateless cryptography, attract great attention from researchers. To resolve these difficulties, Wang et al. designed a new authentication architecture for the WBANs environment, which was claimed to be secure and efficient. However, in this paper, we will show that this scheme is prone to ephemeral key leakage attacks. Further, based on this authentication scheme, an anonymous certificateless scheme is proposed for lightweight devices. Meanwhile, user anonymity is fully protected. The proposed scheme is proved to be secure under a specific security model. In addition, we assess the security attributes our scheme meets through BAN logic and Scyther tool. The comparisons of time consumption and communication cost are given at the end of the paper, to demonstrate that our scheme performs prior to several previous schemes.

Graph convolutional networks (GCNs) have become prevalent in recommender system (RS) due to their superiority in modeling collaborative patterns. Although improving the overall accuracy, GCNs unfortunately amplify popularity bias — tail items are less likely to be recommended. This effect prevents the GCN-based RS from making precise and fair recommendations, decreasing the effectiveness of recommender systems in the long run.

In this paper, we investigate how graph convolutions amplify the popularity bias in RS. Through theoretical analyses, we identify two fundamental factors: (1) with graph convolution (i.e., neighborhood aggregation), popular items exert larger influence than tail items on neighbor users, making the users move towards popular items in the representation space; (2) after multiple times of graph convolution, popular items would affect more high-order neighbors and become more influential. The two points make popular items get closer to almost users and thus being recommended more frequently. To rectify this, we propose to estimate the amplified effect of popular nodes on each node’s representation, and intervene the effect after each graph convolution. Specifically, we adopt clustering to discover highly-influential nodes and estimate the amplification effect of each node, then remove the effect from the node embeddings at each graph convolution layer. Our method is simple and generic — it can be used in the inference stage to correct existing models rather than training a new model from scratch, and can be applied to various GCN models. We demonstrate our method on two representative GCN backbones LightGCN and UltraGCN, verifying its ability in improving the recommendations of tail items without sacrificing the performance of popular items. Codes are open-sourced

See github.com/MEICRS/DAP website.

.

Blockchain as a decentralized storage technology is widely used in many fields. It has extremely strict requirements for reliability because there are many potentially malicious nodes. Generally, blockchain is a chain storage structure formed by interconnecting blocks

A block is consist of a block header and a block body. The metadata is stored in block header and data is stored in block body.

, which are stored by full replication method, where each node stores a replica of all blocks and the data consistency is maintained by the consensus protocol. To decrease the storage overhead, previous approaches such as BFT-Store and Partition Chain store blocks via erasure codes. However, existing erasure coding based methods utilize static encoding schema to tolerant f malicious nodes, but in the typical cases, the number of malicious nodes is much smaller than f as described in previous literatures. Using redundant parities to tolerate excessive malicious nodes introduces unnecessary storage overhead.

To solve the above problem, we propose Dynamic-EC, which is a Dynamic Erasure Coding method in permissioned blockchain systems. The key idea of Dynamic-EC is to reduce the storage overhead by dynamically adjusting the total number of parities according to the risk level of the whole system, which is determined by the number of perceived malicious nodes, while ensuring the system reliability. To demonstrate the effectiveness of Dynamic-EC, we conduct several experiments on an open source blockchain software Tendermint. The results show that, compared to the state-of-the-art erasure coding methods, Dynamic-EC reduces the storage overhead by up to 42%, and decreases the average write latency of blocks by up to 25%, respectively.

As deep neural networks (DNNs) have been successfully adopted in various domains, the training of these large-scale models becomes increasingly difficult and is often deployed on compute clusters composed of many devices like GPUs. However, as the size of the cluster increases, so does the possibility of failures during training. Currently, faults are mainly handled by recording checkpoints and recovering, but this approach causes large overhead and affects the training efficiency even when no error occurs. The low checkpointing frequency leads to a large loss of training time, while the high recording frequency affects the training efficiency. To solve this contradiction, we propose BAFT, a bubble-aware fault tolerant framework for hybrid parallel distributed training. BAFT can automatically analyze parallel strategies, profile the runtime information, and schedule checkpointing tasks at the granularity of pipeline stage depending on the bubble distribution in the training. It supports higher checkpoint efficiency and only introduces less than 1% time overhead, which allows us to record checkpoints at high frequency, thereby reducing the time loss in error recovery and avoiding the impact of fault tolerance on training.

Association in-between features has been demonstrated to improve the representation ability of data. However, the original association data reconstruction method may face two issues: the dimension of reconstructed data is undoubtedly higher than that of original data, and adopted association measure method does not well balance effectiveness and efficiency. To address above two issues, this paper proposes a novel association-based representation improvement method, named as AssoRep. AssoRep first obtains the association between features via distance correlation method that has some advantages than Pearson’s correlation coefficient. Then an improved matrix is formed via stacking the association value of any two features. Next, an improved feature representation is obtained by aggregating the original feature with the enhancement matrix. Finally, the improved feature representation is mapped to a low-dimensional space via principal component analysis. The effectiveness of AssoRep is validated on 120 datasets and the fruits further prefect our previous work on the association data reconstruction.