GraphDAFI: A graph representation learning framework with degree-aware feature interaction for node classification

i

This article has been updated. A Correction to this article was published on .

i

The Original Article was published on

i

The Original Article was published on

i

This article has been updated

i

This article was retracted on

i

This article has been updated

Abstract

Graph neural networks (GNNs) have been widely studied to handle graph-structured data due to their superior learning capability. Despite the successful applications of GNNs in many areas, their performance suffers heavily from the imbalanced degree distribution (long-tail issue). Most prior studies tackle this issue by graph augmentation, which explicitly increases the communication among nodes by optimizing original topology. In this paper, we employed the perspective of taylor interaction to explore the long-tail issue, and analyzed that there is insufficient interaction between low-degree nodes and their neighbors. In detail, we proposed a novel GNN framework named with degree-aware feature interaction (GraphDAFI), in order to bridge the gap of neighborhood aggregation between head-node embeddings and tail-node embeddings. GraphDAFI comprises two collaborative modules: adaptive feature interaction and degree-aware neighborhood transfer. Adaptive feature interaction leverages node embeddings of the current layer and interactions of the historical layer to perceive potential local information. Then, a unified feature encoder was designed that enhances the interaction to increase the model’s generalization ability. To inject relevant information into low-degree nodes, a degree-aware neighborhood transfer was developed, which updates the node-edge adjacency matrix through a degree-aware strategy to achieve knowledge transfer. Experimental results demonstrate that GraphDAFI achieves excellent performance in semi-supervised node classification compared with the state-of-the-art models.

Keywords

semi-supervised learning / graph neural network / imbalance learning / knowledge transfer / feature interaction

CHANGE HISTORY

A Correction to this paper has been published:
https://doi.org

The Retraction Note was updated to reflect reception of statements of disagreement from all authors.

This article has been retracted.Please see the Retraction Notice for more detail:
https://doi.org

References

[1] S. Khoshraftar, A. An, A survey on graph representation learning methods, ACM Trans. Intell. Syst. Technol., 15 (2024), 1-55. https://doi.org/10.1145/3633518

[2] K. Sharma, Y. Lee, S. Nambi, A. Salian, S. Shah, S. Kim, et al., A survey of graph neural networks for social recommender systems, ACM Comput. Surv., 56 (2024), 1-34. https://doi.org/10.1145/3661821

[3] M. Réau, N. Renaud, L. C. Xue, A. M. J. J. Bonvin, DeepRank-GNN: A graph neural network framework to learn patterns in protein-protein interfaces, Bioinformatics, 39 (2023), 759. https://doi.org/10.1093/bioinformatics/btac759

[4] F. Li, J. Feng, H. Yan, G. Jin, F. Yang, F. Sun, et al., Dynamic graph convolutional recurrent network for traffic prediction: Benchmark and solution, ACM Trans. Knowl. Discovery Data, 17 (2023), 1-21. https://doi.org/10.1145/3532611

[5] X. Pei, X. Deng, N. N. Xiong, S. Mumtaz, J. Wu, Complex graph analysis and representation learning: Problems, techniques, and applications, IEEE Trans. Network Sci. Eng., 11 (2024), 4990-5007. https://doi.org/10.1109/TNSE.2024.3417850

[6] Q. Guo, X. Yang, F. Zhang, T. Xu, Perturbation-augmented graph convolutional networks: A graph contrastive learning architecture for effective node classification tasks, Eng. Appl. Artif. Intell., 129 (2024), 107616. https://doi.org/10.1016/j.engappai.2023.107616

[7] Y. Ye, S. Ji, Sparse graph attention networks, IEEE Trans. Knowl. Data Eng., 35 (2023), 905-916. https://doi.org/10.1109/TKDE.2021.3072345

[8] F. Wu, T. Zhang, A. H. de Souza Jr., C. Fifty, T. Yu, K. Q. Weinberger, Simplifying graph convolutional networks, preprint, arXiv:1902.07153.

[9] S. Yi, Z. Mao, W. Ju, Y. Zhou, L. Liu, X. Luo, Towards long-tailed recognition for graph classification via collaborative experts, IEEE Trans. Big Data, 9 (2023), 1683-1696. https://doi.org/10.1109/TBDATA.2023.3313029

[10] X. Wang, X. Yang, P. Wang, H. Yu, T. Xu, SSGCN: A sampling sequential guided graph convolutional network, Int. J. Mach. Learn. Cybern., 15 (2024), 2023-2038. https://doi.org/10.1007/s13042-023-02013-2

[11] Z. Liu, W. Zhang, Y. Fang, X. Zhang, S. C. H. Hoi, Towards locality-aware meta-learning of tail node embeddings on networks, in Proceedings of the 29th ACM International Conference on Information & Knowledge Management, (2020), 975-984. https://doi.org/10.1145/3340531.3411910

[12] E. M. Hamedani, M. Kaedi, Recommending the long tail items through personalized diversification, Knowl.-Based Syst., 164 (2019), 348-357. https://doi.org/10.1016/j.knosys.2018.11.004

[13] K. Yao, J. Liang, J. Liang, M. Li, F. Cao, Multi-view graph convolutional networks with attention mechanism, Artif. Intell., 307 (2022), 103708. https://doi.org/10.1016/j.artint.2022.103708

[14] J. Lin, Y. Wan, J. Xu, X. Qi, Long-tailed graph neural networks via graph structure learning for node classification, Appl. Intell., 53 (2023), 20206-20222. https://doi.org/10.1007/s10489-023-04534-3

[15] Z. Liu, T. Nguyen, Y. Fang, Tail-GNN: Tail-node graph neural networks, in Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, (2021), 1109-1119. https://doi.org/10.1145/3447548.3467276

[16] S. Zhu, C. Zhou, S. Pan, X. Zhu, B. Wang, Relation structure-aware heterogeneous graph neural network, in 2019 IEEE International Conference on Data Mining (ICDM), (2019), 1534-1539. https://doi.org/10.1109/ICDM.2019.00203

[17] L. Liang, Z. Xu, Z. Song, I. King, Y. Qi, J. Ye, Tackling long-tailed distribution issue in graph neural networks via normalization, IEEE Trans. Knowl. Data Eng., 36 (2024), 2213-2223. https://doi.org/10.1109/TKDE.2023.3315284

[18] H. Deng, N. Zou, M. Du, W. Chen, G. Feng, Z. Yang, et al., Unifying fourteen post-hoc attribution methods with taylor interactions, IEEE Trans. Pattern Anal. Mach. Intell., 46 (2024), 4625-4640. https://doi.org/10.1109/TPAMI.2024.3358410

[19] F. Hu, Y. Zhu, S. Wu, W. Huang, L. Wang, T. Tan, GraphAIR: Graph representation learning with neighborhood aggregation and interaction, Pattern Recognit., 112 (2021), 107745. https://doi.org/10.1016/j.patcog.2020.107745

[20] J. Gao, J. Gao, X. Ying, M. Lu, J. Wang, Higher-order interaction goes neural: A substructure assembling graph attention network for graph classification, IEEE Trans. Knowl. Data Eng., 35 (2023), 1594-1608. https://doi.org/10.1109/TKDE.2021.3105544

[21] A. Kazi, L. Cosmo, S. Ahmadi, N. Navab, M. M. Bronstein, Differentiable graph module (DGM) for graph convolutional networks, IEEE Trans. Pattern Anal. Mach. Intell., 45 (2023), 1606-1617. https://doi.org/10.1109/TPAMI.2022.3170249

[22] J. Lian, X. Zhou, F. Zhang, Z. Chen, X. Xie, G. Sun, xDeepFM: Combining explicit and implicit feature interactions for recommender systems, in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, (2018), 1754-1763. https://doi.org/10.1145/3219819.3220023

[23] Z. Shen, Z. Kang, When heterophily meets heterogeneous graphs: Latent graphs guided unsupervised representation learning, IEEE Trans. Neural Networks Learn. Syst., 36 (2025), 10283-10296. https://doi.org/10.1109/TNNLS.2025.3540063

[24] S. Yun, K. Kim, K. Yoon, C. Park, LTE4G: Long-tail experts for graph neural networks, in Proceedings of the 31st ACM International Conference on Information & Knowledge Management, (2022), 2434-2443. https://doi.org/10.1145/3511808.3557381

[25] J. Wu, J. He, J. Xu, DEMO-Net: Degree-specific graph neural networks for node and graph classification, in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, (2019), 406-415. https://doi.org/10.1145/3292500.3330950

[26] X. Jiang, R. Zhu, P. Ji, S. Li, Co-Embedding of nodes and edges with graph neural networks, IEEE Trans. Pattern Anal. Mach. Intell., 45 (2023), 7075-7086. https://doi.org/10.1109/TPAMI.2020.3029762

[27] X. Tang, H. Yao, Y. Sun, Y. Wang, J. Tang, C. Aggarwal, et al., Investigating and mitigating degree-related biases in graph convolutional networks, in Proceedings of the 29th ACM International Conference on Information & Knowledge Management, (2020), 1435-1444. https://doi.org/10.1145/3340531.3411872

[28] Z. Zhao, Z. Yang, C. Li, Q. Zeng, W. Guan, M. Zhou, Dual feature interaction-based graph convolutional network, IEEE Trans. Knowl. Data Eng., 35 (2023), 9019-9030. https://doi.org/10.1109/TKDE.2022.3220789

[29] W. Cheng, Y. Shen, L. Huang, Adaptive factorization network: learning adaptive-order feature interactions, in Proceedings of the AAAI Conference on Artificial Intelligence, 34 (2020), 3609-3616. https://doi.org/10.1609/aaai.v34i04.5768

[30] M. Guang, C. Yan, Y. Xu, J. Wang, C. Jiang, Graph convolutional networks with adaptive neighborhood awareness, IEEE Trans. Pattern Anal. Mach. Intell., 46 (2024), 7392-7404. https://doi.org/10.1109/TPAMI.2024.3391356

[31] W. Guan, X. Yang, M. Li, Q. Guo, K. Liu, Q. Sun, VQIT-GNN: A collaborative knowledge transfer for node-level structure imbalance, Pattern Recognit., 172 (2026), 112632. https://doi.org/10.1016/j.patcog.2025.112632

[32] P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, Y. Bengio, Graph attention networks, preprint, arXiv:1710.10903.

[33] G. Zhu, K. Liu, X. Yang, Q. Guo, UMGCN: Updating multi-graph for graph convolutional networks, Comput. Electr. Eng., 123 (2025), 109957. https://doi.org/10.1016/j.compeleceng.2024.109957

[34] Q. Guo, X. Yang, M. Li, Y. Qian, Collaborative graph neural networks for augmented graphs: a local-to-global perspective, Pattern Recognit., 158 (2025), 111020. https://doi.org/10.1016/j.patcog.2024.111020

[35] H. Cong, X. Yang, K. Liu, Q. Guo, Feature-topology cascade perturbation for graph neural network, Eng. Appl. Artif. Intell., 152 (2025), 110657. https://doi.org/10.1016/j.engappai.2025.110657