Soft-GNN: towards robust graph neural networks via self-adaptive data utilization

doi:10.1007/s11704-024-3575-5

Front. Comput. Sci.

2025, Vol. 19

Issue (4) : 194311 https://doi.org/10.1007/s11704-024-3575-5

Artificial Intelligence

Soft-GNN: towards robust graph neural networks via self-adaptive data utilization

Yao WU^1,², Hong HUANG¹(

), Yu SONG³, Hai JIN¹

¹. National Engineering Research Center for Big Data Technology and System, Service Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
². College of Information and Communication, National University of Defense Technology, Wuhan 430019, China
³. Department of Computer Science and Operations Research, Université de Montréal, Montreal H3C 3J7, Canada

Download: PDF(4430 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Graph neural networks (GNNs) have gained traction and have been applied to various graph-based data analysis tasks due to their high performance. However, a major concern is their robustness, particularly when faced with graph data that has been deliberately or accidentally polluted with noise. This presents a challenge in learning robust GNNs under noisy conditions. To address this issue, we propose a novel framework called Soft-GNN, which mitigates the influence of label noise by adapting the data utilized in training. Our approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation, local deviation, and global deviation. By better utilizing significant training samples and reducing the impact of label noise through dynamic data selection, GNNs are trained to be more robust. We evaluate the performance, robustness, generality, and complexity of our model on five real-world datasets, and our experimental results demonstrate the superiority of our approach over existing methods.

Keywords graph neural networks node classification label noise robustness

Corresponding Author(s): Hong HUANG

Just Accepted Date: 22 March 2024 Issue Date: 14 May 2024

Cite this article:

Yao WU,Hong HUANG,Yu SONG, et al. Soft-GNN: towards robust graph neural networks via self-adaptive data utilization[J]. Front. Comput. Sci., 2025, 19(4): 194311.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-024-3575-5
https://academic.hep.com.cn/fcs/EN/Y2025/V19/I4/194311

Fig.1 (a) The performance of GCN under different levels of noise rate on Cora and Citeseer. The “-NF” dataset is derived from the noisy dataset by eliminating the noise labels; (b) the loss curve of GCN trained on Cora under noise rate=0.3

Fig.2 (a) The KL-divergence of the prediction distributions between nodes and local surrounding nodes; (b) the NDCG@10 of ranking similar nodes based on feature space in the output space. We get the results on Cora with GCN when the noise rate is 0.3

Fig.3 The overall framework of Soft-GNN

Tab.1 The statistics of five datasets

Dataset	Noise type	Backbone	Method
Dataset	Noise type	Backbone	Basic	Co-teaching	Decoupling	Trunc $L q$	SACE	UnionNET	SuLD-GNN	NRGNN	CLNode	ours
Cora	Uniform	GCN	73.02±0.53	61.87±1.05	72.66±0.44	72.62±0.49	69.98±0.43	71.32±0.72	73.10±0.54	74.43±0.52	75.49±0.68	76.25±0.57
	Uniform	APPNP	77.64±0.77	64.24±1.28	77.69±0.76	74.13±1.04	75.02±0.95	73.33±1.30	78.16±0.77	?	77.85±0.71	78.70±0.71
	Pair	GCN	78.43±0.31	71.15±0.51	78.19±0.31	78.48±0.46	78.38±0.36	78.20±0.36	79.16±0.26	78.69±0.59	79.07±0.46	79.49±0.48
	Pair	APPNP	81.60±1.01	76.29±1.63	81.27±0.84	81.46±0.82	81.91±0.89	81.51±0.65	81.26±0.69	?	82.68±0.42	83.66±0.37
Citeseer	Uniform	GCN	65.27±0.72	59.03±0.96	64.97±0.79	64.84±0.80	66.08±0.81	66.07±1.07	65.07±0.60	67.22±0.75	67.91±0.67	68.40±0.70
	Uniform	APPNP	71.05±0.68	69.75±0.73	70.50±0.77	71.00±0.59	71.86±0.60	70.75±0.71	71.00±0.79	?	71.64±0.72	71.97±0.74
	Pair	GCN	65.62±0.63	61.31±1.16	65.58±0.56	67.00±0.75	66.25±0.66	65.80±1.15	65.36±0.67	66.56±0.82	67.94±0.52	68.11±0.56
	Pair	APPNP	69.46±0.87	67.35±0.80	69.12±0.80	69.95±0.88	70.07±0.62	69.23±0.65	67.44±0.77	?	70.78±0.44	71.98±0.40
Pubmed	Uniform	GCN	72.36±1.16	71.76±1.06	72.29±1.11	72.30±1.17	72.84±1.17	72.28±1.12	70.48±1.52	68.46±1.54	72.96±0.99	73.08±1.11
	Uniform	APPNP	74.67±2.02	73.88±1.75	74.37±2.06	75.07±2.05	74.89±1.97	74.35±1.95	72.42±2.73	?	74.90±1.02	75.65±2.31
	Pair	GCN	70.21±0.84	66.68±1.85	70.09±0.86	70.81±1.01	71.42±1.07	69.85±0.87	69.22±0.89	68.75±0.77	70.23±1.08	71.02±0.87
	Pair	APPNP	74.92±1.07	74.39±1.36	74.16±1.25	75.49±1.14	75.40±1.09	74.63±1.08	74.42±1.04	?	75.92±0.85	76.13±1.02
Wiki-cs	Uniform	GCN	56.99±0.53	58.24±0.91	56.96±0.51	49.84±1.04	51.66±0.98	48.94±1.73	53.87±1.10	55.23±1.13	56.75±0.67	58.04±0.63
	Uniform	APPNP	67.55±0.73	67.71±0.66	66.33±0.77	62.61±1.23	64.45±0.86	60.42±2.19	56.03±2.29	?	67.29±0.65	68.81±0.91
	Pair	GCN	55.36±0.47	56.39±0.45	55.63±0.49	51.34±0.83	52.42±0.79	49.68±1.37	53.53±1.21	54.37±0.74	55.06±0.49	56.87±1.04
	Pair	APPNP	65.72±0.41	66.54±0.51	64.56±0.49	61.91±0.72	62.94±0.62	58.74±1.94	54.79±1.69	?	65.11±0.50	66.93±0.70
A-computers	Uniform	GCN	58.01±1.18	58.27±3.00	57.27±3.34	52.76±1.82	53.36±2.25	48.63±2.18	59.01±2.74	?	56.95±1.58	59.89±1.32
	Uniform	APPNP	64.20±1.73	64.83±3.22	65.19±3.71	56.03±5.00	56.88±2.84	52.74±3.89	65.32±3.90	?	64.98±2.23	65.44±1.85
	Pair	GCN	69.25±1.54	68.52±1.79	68.92±1.61	59.91±2.83	60.44±2.32	54.01±6.77	68.88±1.83	?	68.34±1.59	70.43±2.21
	Pair	APPNP	73.98±0.75	71.36±1.79	73.30±0.88	62.28±2.32	63.71±1.88	63.20±3.36	74.51±0.74	?	73.80±0.99	75.11±0.73

Tab.2 The Micro-F1 (%) under uniform and pair noise rate=0.2. We present the results and 95% confidence interval

Fig.4 The results under different noise types and rates on Cora and Citeseer. (a) Uniform; (b) Pair; (c) Uniform; (d) Pair

Fig.5 The performance gains over GCN on Citeseer under noise rate=0.4. (a) Micro-F1; (b) Macro-F1

Ratio to GCN	Time			GPU Memory
Ratio to GCN	Citeseer	Pubmed	Wiki-cs	Citeseer	Pubmed	Wiki-cs
Co-teaching	1.38	1.35	1.31	1.03	1.05	1.02
Trunc $L q$	0.50	0.44	0.52	–	–	–
UnionNET	0.72	0.71	0.73	–	–	–
NRGNN	16.18	70.79	61.09	1.93	1.91	9.35
Soft-GNN	2.00	1.85	3.26	1.04	1.02	–

Tab.3 The comparison of time and memory efficiency over GCN with 64 hidden units

Fig.6 The performance comparison with different hyper-parameters:

q

and

k

on Cora under noise rate=0.3 with GCN

1	B, Wu J, Li C, Hou G, Fu Y, Bian L, Chen J Huang . Recent advances in reliable deep graph learning: adversarial attack, inherent noise, and distribution shift. 2022, arXiv preprint arXiv: 2202.07114
2	S Y, Li S J, Huang S Chen . Crowdsourcing aggregation with deep Bayesian learning. Science China Information Sciences, 2021, 64( 3): 130104
3	N T, Hoang J J, Choong T Murata . Learning graph neural networks with noisy labels. In: Proceedings of the ICLR LLD 2019. 2019
4	D, Zügner A, Akbarnejad S Günnemann . Adversarial attacks on neural networks for graph data. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018, 2847−2856
5	Y, Li J, Yin L Chen . Unified robust training for graph neural networks against label noise. In: Proceedings of the 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining. 2021, 528−540
6	Y, Zhuo X, Zhou J Wu . Training graph convolutional neural network against label noise. In: Proceedings of the 28th International Conference on Neural Information Processing. 2021, 677−689
7	X, Du T, Bian Y, Rong B, Han T, Liu T, Xu W, Huang J Huang . PI-GNN: a novel perspective on semi-supervised node classification against noisy labels. 2021, arXiv preprint arXiv: 2106.07451
8	E, Dai C, Aggarwal S Wang . NRGNN: learning a label noise resistant graph neural network on sparsely and noisily labeled graphs. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021, 227−236
9	T N, Kipf M Welling . Semi-supervised classification with graph convolutional networks. In: Proceedings of ICLR 2017. 2017
10	L, Huang C, Zhang H Zhang . Self-adaptive training: beyond empirical risk minimization. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 1624
11	B, Frenay M Verleysen . Classification in the presence of label noise: a survey. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25( 5): 845–869
12	J, Bootkrajang A Kabán . Classification of mislabelled microarrays using robust sparse logistic regression. Bioinformatics, 2013, 29( 7): 870–877
13	X, Shi W Che . Combating with extremely noisy samples in weakly supervised slot filling for automatic diagnosis. Frontiers of Computer Science, 2023, 17( 5): 175333
14	T, Xiao T, Xia Y, Yang C, Huang X Wang . Learning from massive noisy labeled data for image classification. In: Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015, 2691−2699
15	Q, Tian H, Sun S, Peng T Ma . Self-adaptive label filtering learning for unsupervised domain adaptation. Frontiers of Computer Science, 2023, 17( 1): 171308
16	C, Beck H, Booth M, El-Assady M Butt . Representation problems in linguistic annotations: ambiguity, variation, uncertainty, error and bias. In: Proceedings of the 14th Linguistic Annotation Workshop. 2020, 60−73
17	B, Biggio B, Nelson P Laskov . Support vector machines under adversarial label noise. In: Proceedings of the 3rd Asian Conference on Machine Learning. 2011, 97−112
18	J, Abellán A R Masegosa . An experimental study about simple decision trees for bagging ensemble on datasets with classification noise. In: Proceedings of the 10th European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty. 2009, 446−456
19	R, Wang T, Liu D Tao . Multiclass learning with partially corrupted labels. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29( 6): 2568–2580
20	S, Sigurdsson J, Larsen L K, Hansen P A, Philipsen H C Wulf . Outlier estimation and detection application to skin lesion classification. In: Proceedings of 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing. 2002, 1049−1052
21	C, Bouveyron S Girard . Robust supervised classification with mixture models: learning from data with uncertain labels. Pattern Recognition, 2009, 42( 11): 2649–2658
22	C E, Brodley M A Friedl . Identifying mislabeled training data. Journal of Artificial Intelligence Research, 1999, 11: 131–167
23	J, Thongkam G, Xu Y, Zhang F Huang . Support vector machine for outlier detection in breast cancer survivability prediction. In: Proceedings of the Asia-Pacific Web Conference. 2008, 99−109
24	A L B, Miranda L P F, Garcia A C P L F, Carvalho A C Lorena . Use of classification algorithms in noise detection and elimination. In: Proceedings of the 4th International Conference on Hybrid Artificial Intelligence Systems. 2009, 417−424
25	E, Dedeoglu H T, Kesgin M F Amasyali . A robust optimization method for label noisy datasets based on adaptive threshold: adaptive-k. Frontiers of Computer Science, 2024, 18( 4): 184315
26	Y, Wang A, Kucukelbir D M Blei . Robust probabilistic modeling with Bayesian data reweighting. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 3646−3655
27	L, Jiang Z, Zhou T, Leung L J, Li F F Li . MentorNet: learning data-driven curriculum for very deep neural networks on corrupted labels. In: Proceedings of the 35th International Conference on Machine Learning. 2018, 2304−2313
28	J, Shu Q, Xie L, Yi Q, Zhao S, Zhou Z, Xu D Meng . Meta-weight-net: learning an explicit mapping for sample weighting. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 172
29	D, Nguyen C K, Mummadi T P N, Ngo T H P, Nguyen L, Beggel T Brox . SELF: learning to filter noisy labels with self-ensembling. In: Proceedings of the 8th International Conference on Learning Representations. 2020
30	P, Chen B, Liao G, Chen S Zhang . Understanding and utilizing deep neural networks trained with noisy labels. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 1062−1070
31	G, Zheng A H, Awadallah S Dumais . Meta label correction for noisy label learning. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. 2021, 11053−11061
32	J, Liu R, Li C Sun . Co-correcting: noise-tolerant medical image classification via mutual label correction. IEEE Transactions on Medical Imaging, 2021, 40( 12): 3580–3592
33	E, Malach S Shalev-Shwartz . Decoupling "when to update" from "how to update". In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 961−971
34	B, Han Q, Yao X, Yu G, Niu M, Xu W, Hu I W, Tsang M Sugiyama . Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 8536−8546
35	X, Guo W Wang . Towards making co-training suffer less from insufficient views. Frontiers of Computer Science, 2019, 13( 1): 99–105
36	Gasteiger J, Bojchevski A, Günnemann S. Predict then propagate: Graph neural networks meet personalized pagerank. In: Proceedings of the International Conference on Learning Representations (ICLR). 2019
37	Wei X, Gong X, Zhan Y, Du B, Luo Y, Hu W. CLNode: curriculum learning for node classification. In: Proceedings of the 16th ACM International Conference on Web Search and Data Mining. 2023, 670−678
38	Y, Liu Z, Wu Z, Lu G, Wen J, Ma G, Lu X Zhu . Multi-teacher self-training for semi-supervised node classification with noisy labels. In: Proceedings of the 31st ACM International Conference on Multimedia. 2023, 2946−2954
39	K, Kuang P, Cui S, Athey R, Xiong B Li . Stable prediction across unknown environments. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018, 1617−1626
40	M, Hwang Y, Jeong W Sung . Data distribution search to select core-set for machine learning. In: Proceedings of the 9th International Conference on Smart Media and Applications. 2020, 172−176
41	M, Paul S, Ganguli G K Dziugaite . Deep learning on a data diet: finding important examples early in training. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2021, 20596−20607
42	H, Wang J Leskovec . Unifying graph convolutional neural networks and label propagation. 2020, arXiv preprint arXiv: 2002.06755
43	W, Dong J, Wu Y, Luo Z, Ge P Wang . Node representation learning in graph via node-to-neighbourhood mutual information maximization. In: Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022, 16620−16629
44	S, Hochreiter J Schmidhuber . Long short-term memory. Neural Computation, 1997, 9( 8): 1735–1780
45	P, Sen G, Namata M, Bilgic L, Getoor B, Gallagher T Eliassi-Rad . Collective classification in network data. AI Magazine, 2008, 29( 3): 93–106
46	G, Namata B, London L, Getoor B Huang . Query-driven active surveying for collective classification. In: Proceedings of the Workshop on Mining and Learning with Graphs. 2012
47	P, Mernyei C Cangea . Wiki-CS: a wikipedia-based benchmark for graph neural networks. In: Proceedings of the Graph Representation Learning and Beyond Workshop on ICML. 2020
48	O, Shchur M, Mumme A, Bojchevski S Günnemann . Pitfalls of graph neural network evaluation. 2019, arXiv preprint arXiv: 1811.05868
49	Z, Zhang M R Sabuncu . Generalized cross entropy loss for training deep neural networks with noisy labels. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 8792−8802
50	M, Zhu X, Wang C, Shi H, Ji P Cui . Interpreting and unifying graph neural networks with an optimization framework. In: Proceedings of the Web Conference 2021. 2021, 1215−1226

[1]

FCS-23575-OF-YW_suppl_1

Download

[1]	Shao-Yuan LI, Shi-Ji ZHAO, Zheng-Tao CAO, Sheng-Jun HUANG, Songcan CHEN. Robust domain adaptation with noisy and shifted label distribution[J]. Front. Comput. Sci., 2025, 19(3): 193310-.
[2]	Tao HE, Ming LIU, Yixin CAO, Zekun WANG, Zihao ZHENG, Bing QIN. Exploring & exploiting high-order graph structure for sparse knowledge graph completion[J]. Front. Comput. Sci., 2025, 19(2): 192306-.
[3]	Shangwei WU, Yingtong XIONG, Hui LIANG, Chuliang WENG. D²-GCN: a graph convolutional network with dynamic disentanglement for node classification[J]. Front. Comput. Sci., 2025, 19(1): 191305-.
[4]	Shaoyuan LI, Yuxiang ZHENG, Ye SHI, Shengjun HUANG, Songcan CHEN. KD-Crowd: a knowledge distillation framework for learning from crowds[J]. Front. Comput. Sci., 2025, 19(1): 191302-.
[5]	Lei YUAN, Feng CHEN, Zongzhang ZHANG, Yang YU. Communication-robust multi-agent learning by adaptable auxiliary multi-agent adversary generation[J]. Front. Comput. Sci., 2024, 18(6): 186331-.
[6]	Enes DEDEOGLU, Himmet Toprak KESGIN, Mehmet Fatih AMASYALI. A robust optimization method for label noisy datasets based on adaptive threshold: Adaptive-k[J]. Front. Comput. Sci., 2024, 18(4): 184315-.
[7]	Yuting YANG, Pei HUANG, Juan CAO, Jintao LI, Yun LIN, Feifei MA. A prompt-based approach to adversarial example generation and robustness enhancement[J]. Front. Comput. Sci., 2024, 18(4): 184318-.
[8]	Yongquan LIANG, Qiuyu SONG, Zhongying ZHAO, Hui ZHOU, Maoguo GONG. BA-GNN: Behavior-aware graph neural network for session-based recommendation[J]. Front. Comput. Sci., 2023, 17(6): 176613-.
[9]	Yuan GAO, Xiang WANG, Xiangnan HE, Huamin FENG, Yongdong ZHANG. Rumor detection with self-supervised learning on texts and social graph[J]. Front. Comput. Sci., 2023, 17(4): 174611-.
[10]	Zhe XUE, Junping DU, Xin XU, Xiangbin LIU, Junfu WANG, Feifei KOU. Few-shot node classification via local adaptive discriminant structure learning[J]. Front. Comput. Sci., 2023, 17(2): 172316-.
[11]	Min GAO, Bin LING, Linda YANG, Junhao WEN, Qingyu XIONG, Shun LI. From similarity perspective: a robust collaborative filtering approach for service recommendations[J]. Front. Comput. Sci., 2019, 13(2): 231-246.
[12]	Jing LIU, Mingxing ZHOU, Shuai WANG, Penghui LIU. A comparative study of network robustness measures[J]. Front. Comput. Sci., 2017, 11(4): 568-584.
[13]	Yaochu JIN, Robin GRUNA, Bernhard SENDHOFF. Pareto analysis evolutionary and learning systems[J]. Front Comput Sci Chin, 2009, 3(1): 4-17.

Viewed

Full text

Abstract

Cited

Shared

Discussed