Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Core Knowledge Learning Framework for Graph Adaptation and Scalability Learning (2407.01886v1)

Published 2 Jul 2024 in cs.LG and cs.AI

Abstract: Graph classification is a pivotal challenge in machine learning, especially within the realm of graph-based data, given its importance in numerous real-world applications such as social network analysis, recommendation systems, and bioinformatics. Despite its significance, graph classification faces several hurdles, including adapting to diverse prediction tasks, training across multiple target domains, and handling small-sample prediction scenarios. Current methods often tackle these challenges individually, leading to fragmented solutions that lack a holistic approach to the overarching problem. In this paper, we propose an algorithm aimed at addressing the aforementioned challenges. By incorporating insights from various types of tasks, our method aims to enhance adaptability, scalability, and generalizability in graph classification. Motivated by the recognition that the underlying subgraph plays a crucial role in GNN prediction, while the remainder is task-irrelevant, we introduce the Core Knowledge Learning (\method{}) framework for graph adaptation and scalability learning. \method{} comprises several key modules, including the core subgraph knowledge submodule, graph domain adaptation module, and few-shot learning module for downstream tasks. Each module is tailored to tackle specific challenges in graph classification, such as domain shift, label inconsistencies, and data scarcity. By learning the core subgraph of the entire graph, we focus on the most pertinent features for task relevance. Consequently, our method offers benefits such as improved model performance, increased domain adaptability, and enhanced robustness to domain variations. Experimental results demonstrate significant performance enhancements achieved by our method compared to state-of-the-art approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (78)
  1. Low data drug discovery with one-shot learning. ACS central science 3, 4 (2017), 283–293.
  2. Accurate Learning of Graph Representations with Graph Multiset Pooling. In Proceedings of the International Conference on Learning Representations.
  3. Weisfeiler and lehman go cellular: Cw networks. In Proceedings of the Conference on Neural Information Processing Systems. 2625–2640.
  4. A hyperbolic-to-hyperbolic graph convolutional network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 154–163.
  5. Graph transfer learning via adversarial domain adaptation with graph convolution. IEEE Transactions on Knowledge and Data Engineering 35, 5 (2022), 4908–4922.
  6. Graph prototypical networks for few-shot learning on attributed networks. In Proceedings of the International Conference on Information and Knowledge Management. 295–304.
  7. A closer look at distribution shifts and out-of-distribution generalization on graphs. In Proceedings of the International Conference on Neural Information Processing Systems Workshop.
  8. Paul D Dobson and Andrew J Doig. 2003. Distinguishing enzyme structures from non-enzymes without alignments. Journal of molecular biology 330, 4 (2003), 771–783.
  9. Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels. In Proceedings of the Conference on Neural Information Processing Systems. 5724–5734.
  10. Graph neural networks for social recommendation. In Proceedings of the ACM Web Conference. 417–426.
  11. Towards Open Temporal Graph Neural Networks. arXiv preprint arXiv:2303.15015 (2023).
  12. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the International Conference on Machine Learning. 1126–1135.
  13. Concrete dropout. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 30.
  14. Domain-adversarial training of neural networks. The Journal of Machine Learning Research. 17, 1 (2016), 2096–2030.
  15. Edgar N Gilbert. 1959. Random graphs. The Annals of Mathematical Statistics 30, 4 (1959), 1141–1144.
  16. Learning Adaptive Node Embeddings across Graphs. IEEE Transactions on Knowledge and Data Engineering (2022).
  17. Inductive representation learning on large graphs. In Proceedings of the Conference on Neural Information Processing Systems.
  18. ASGN: An active semi-supervised graph neural network for molecular property prediction. In Proceedings of the International ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 731–752.
  19. Hierarchical Graph Convolutional Networks for Semi-Supervised Node Classification. In Proceedings of the International Joint Conference on Artificial Intelligence. 4532–4539.
  20. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016).
  21. A survey of graph neural networks in real world: Imbalance, noise, privacy and ood challenges. arXiv preprint arXiv:2403.04468 (2024).
  22. SUSAN: The Structural Similarity Random Walk Kernel. In Proceedings of the SIAM International Conference on Data Mining. 298–306.
  23. Derivation and validation of toxicophores for mutagenicity prediction. Journal of medicinal chemistry 48, 1 (2005), 312–320.
  24. Edge-labeling graph neural network for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11–20.
  25. Thomas N Kipf and Max Welling. 2017a. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations.
  26. Thomas N. Kipf and Max Welling. 2017b. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of the International Conference on Learning Representations.
  27. Siamese neural networks for one-shot image recognition. In Proceedings of the International Conference on Machine Learning Workshop, Vol. 2. Lille.
  28. kGCN: a graph-based deep learning framework for chemical structures. Journal of Cheminformatics 12 (2020), 1–10.
  29. Greg Landrum et al. 2013. RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling. Greg Landrum 8, 31.10 (2013), 5281.
  30. Dong-Hyun Lee et al. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML. 896.
  31. Jure Leskovec and Christos Faloutsos. 2006. Sampling from large graphs. In Proceedings of the International ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 631–636.
  32. Gated Graph Sequence Neural Networks. In Proceedings of the International Conference on Learning Representations.
  33. Meta-sgd: Learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835 (2017).
  34. Self-supervised consensus representation learning for attributed graph. In Proceedings of the ACM International Conference on Multimedia. 2654–2662.
  35. Learning to propagate labels: Transductive propagation network for few-shot learning. arXiv preprint arXiv:1805.10002 (2018).
  36. Relative and absolute location embedding for few-shot node classification on graph. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4267–4275.
  37. Learning transferable features with deep adaptation networks. In Proceedings of the International Conference on Machine Learning. 97–105.
  38. Conditional adversarial domain adaptation. In Proceedings of the Conference on Neural Information Processing Systems.
  39. Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels. In Proceedings of the ACM Web Conference. 1204–1214.
  40. Parameterized explainer for graph neural network. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 33. 19620–19631.
  41. A flexible generative framework for graph-based semi-supervised learning. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 32.
  42. Adaptive-step graph meta-learner for few-shot graph classification. In Proceedings of the International Conference on Information and Knowledge Management. 1055–1064.
  43. TUDataset: A collection of benchmark datasets for learning with graphs. In Proceedings of the International Conference on Machine Learning Workshop.
  44. Propagation kernels: efficient graph kernels from propagated information. Machine Learning 102, 2 (2016), 209–245.
  45. Graph invariant kernels. In Proceedings of the International Joint Conference on Artificial Intelligence. 3756–3762.
  46. Sa-gda: Spectral augmentation for graph domain adaptation. In Proceedings of the 31st ACM International Conference on Multimedia. 309–318.
  47. Attention-driven Graph Clustering Network. In Proceedings of the ACM International Conference on Multimedia. 935–943.
  48. Sachin Ravi and Hugo Larochelle. 2016. Optimization as a model for few-shot learning. In Proceedings of the International Conference on Learning Representations.
  49. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. In Proceedings of the International Conference on Learning Representations.
  50. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research 12, 9 (2011).
  51. Prototypical networks for few-shot learning. Proceedings of the Conference on Neural Information Processing Systems 30 (2017).
  52. Spline-fitting with a genetic algorithm: A method for developing classification structure- activity relationships. Journal of Chemical Information and Computer Sciences (2003).
  53. Adversarial discriminative domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7167–7176.
  54. Matching networks for one shot learning. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 29.
  55. Is Visual Context Really Helpful for Knowledge Graph? A Representation Learning Perspective. In Proceedings of the ACM International Conference on Multimedia. 2735–2743.
  56. Property-aware relation networks for few-shot molecular property prediction. Proceedings of the Conference on Neural Information Processing Systems 34 (2021), 17441–17454.
  57. Curgraph: Curriculum learning for graph classification. In Proceedings of the Web Conference. 1238–1248.
  58. Metaalign: Coordinating domain alignment and classification for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16643–16653.
  59. ToAlign: Task-Oriented Alignment for Unsupervised Domain Adaptation. In Proceedings of the Conference on Neural Information Processing Systems. 13834–13846.
  60. Attraction and repulsion: Unsupervised domain adaptive graph contrastive learning network. IEEE Transactions on Emerging Topics in Computational Intelligence 6, 5 (2022), 1079–1091.
  61. Discrimination-Aware Mechanism for Fine-grained Representation Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 813–822.
  62. How powerful are graph neural networks?. In Proceedings of the International Conference on Learning Representations.
  63. Heterogeneous graph attention network for unsupervised multiple-target domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 4 (2020), 1992–2003.
  64. David Yarowsky. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In 33rd annual meeting of the association for computational linguistics. 189–196.
  65. From local structures to size generalization in graph neural networks. In Proceedings of the International Conference on Machine Learning. 11975–11986.
  66. Dynamic hypergraph convolutional network. In 2022 IEEE 38th International Conference on Data Engineering (ICDE). IEEE, 1621–1634.
  67. Nan Yin and Zhigang Luo. 2022. Generic structure extraction with bi-level optimization for graph structure learning. Entropy 24, 9 (2022), 1228.
  68. DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification. In Proceedings of the ACM International Conference on Multimedia. 3470–3479.
  69. Coco: A coupled contrastive framework for unsupervised domain adaptive graph classification. In International Conference on Machine Learning. PMLR, 40040–40053.
  70. CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification. In Proceedings of the International Conference on Machine Learning. 40040–40053.
  71. Omg: Towards effective graph classification against label noise. IEEE Transactions on Knowledge and Data Engineering 35, 12 (2023), 12873–12886.
  72. Messages are never propagated alone: Collaborative hypergraph neural network for time-series forecasting. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).
  73. Continuous Spiking Graph Neural Networks. arXiv preprint arXiv:2404.01897 (2024).
  74. Dynamic spiking graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 16495–16503.
  75. DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption. In Proceedings of the International Conference on Learning Representations.
  76. Gnnexplainer: Generating explanations for graph neural networks. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 32.
  77. Mind the label shift of augmentation-based graph ood generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11620–11630.
  78. Transfer learning of graph neural networks with ego-graph information maximization. Advances in Neural Information Processing Systems 34 (2021), 1766–1779.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Bowen Zhang (161 papers)
  2. Zhichao Huang (17 papers)
  3. Genan Dai (11 papers)
  4. Guangning Xu (4 papers)
  5. Xiaomao Fan (13 papers)
  6. Hu Huang (11 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now