Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation (2403.01467v1)

Published 3 Mar 2024 in cs.LG and cs.AI

Abstract: Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. However, most methods require a labelled source graph to provide supervision signals, which might not be accessible in the real-world settings due to regulations and privacy concerns. In this paper, we explore the scenario of source-free unsupervised graph domain adaptation, which tries to address the domain adaptation problem without accessing the labelled source graph. Specifically, we present a novel paradigm called GraphCTA, which performs model adaptation and graph adaptation collaboratively through a series of procedures: (1) conduct model adaptation based on node's neighborhood predictions in target graph considering both local and global information; (2) perform graph adaptation by updating graph structure and node attributes via neighborhood contrastive learning; and (3) the updated graph serves as an input to facilitate the subsequent iteration of model adaptation, thereby establishing a collaborative loop between model adaptation and graph adaptation. Comprehensive experiments are conducted on various public datasets. The experimental results demonstrate that our proposed model outperforms recent source-free baselines by large margins.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (70)
  1. Wasserstein generative adversarial networks. In ICML. PMLR, 214–223.
  2. Analysis of representations for domain adaptation. NIPS 19 (2006).
  3. Graph neural networks with convolutional arma filters. TPAMI 44, 7 (2021), 3496–3507.
  4. A simple framework for contrastive learning of visual representations. In ICML. PMLR, 1597–1607.
  5. Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situations. In CVPR. 3941–3950.
  6. Graph transfer learning via adversarial domain adaptation with graph convolution. TKDE (2022).
  7. Convolutional neural networks on graphs with fast localized spectral filtering. NIPS 29 (2016).
  8. Ailin Deng and Bryan Hooi. 2021. Graph neural network-based anomaly detection in multivariate time series. In AAAI. 4027–4035.
  9. Graph neural networks for social recommendation. In The world wide web conference. 417–426.
  10. SLAPS: Self-supervision improves structure learning for graph neural networks. NIPS 34 (2021), 22667–22681.
  11. Matthias Fey and Jan Eric Lenssen. 2019. Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428 (2019).
  12. Learning discrete structures for graph neural networks. In ICML. PMLR, 1972–1982.
  13. Robustness of graph neural networks at scale. NIPS 34 (2021), 7637–7649.
  14. Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In KDD. 855–864.
  15. Inductive representation learning on large graphs. NIPS 30 (2017).
  16. Momentum contrast for unsupervised visual representation learning. In CVPR. 9729–9738.
  17. Cycada: Cycle-consistent adversarial domain adaptation. In ICML. Pmlr, 1989–1998.
  18. CEDe: A collection of expert-curated datasets with atom-level entity annotations for Optical Chemical Structure Recognition. NIPS 35 (2022), 27114–27126.
  19. Empowering graph representation learning with test-time graph transformation. arXiv preprint arXiv:2210.03561 (2022).
  20. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  21. Thomas N Kipf and Max Welling. 2016a. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
  22. Thomas N Kipf and Max Welling. 2016b. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016).
  23. Confidence score for source-free unsupervised domain adaptation. In ICML. PMLR, 12365–12377.
  24. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In ICML. PMLR, 6028–6039.
  25. Domain adaptation with auxiliary target domain-oriented classifier. In CVPR. 16632–16642.
  26. Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. TPAMI 44, 11 (2021), 8602–8617.
  27. Rethinking Propagation for Unsupervised Graph Domain Adaptation. arXiv preprint arXiv:2402.05660 (2024).
  28. Sparsity-aware sensor collaboration for linear coherent estimation. IEEE Transactions on Signal Processing 63, 10 (2015), 2582–2596.
  29. Towards unsupervised deep graph structure learning. In Proceedings of the ACM Web Conference 2022. 1392–1403.
  30. Learning transferable features with deep adaptation networks. In ICML. PMLR, 97–105.
  31. Conditional adversarial domain adaptation. NIPS 31 (2018).
  32. Unsupervised domain adaptation with residual transfer networks. NIPS 29 (2016).
  33. Deep transfer learning with joint adaptation networks. In ICML. PMLR, 2208–2217.
  34. Source free unsupervised graph domain adaptation. arXiv preprint arXiv:2112.00955 (2021).
  35. Transferrable prototypical networks for unsupervised domain adaptation. In CVPR. 2239–2247.
  36. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In AAAI. 5363–5370.
  37. Deepwalk: Online learning of social representations. In KDD. 701–710.
  38. Multi-scale attributed node embedding. Journal of Complex Networks 9, 2 (2021), cnab014.
  39. Wasserstein distance guided representation learning for domain adaptation. In AAAI, Vol. 32.
  40. Adversarial deep network embedding for cross-network node classification. In AAAI. 2991–2999.
  41. Network together: Node classification via cross-network deep network embedding. TNNLS 32, 5 (2020), 1935–1948.
  42. Ankit Singh. 2021. Clda: Contrastive learning for semi-supervised domain adaptation. NIPS 34 (2021), 5089–5101.
  43. Correlation alignment for unsupervised domain adaptation. Domain adaptation in computer vision applications (2017), 153–171.
  44. Rethinking graph neural networks for anomaly detection. In ICML. PMLR, 21076–21089.
  45. Arnetminer: extraction and mining of academic social networks. In KDD. 990–998.
  46. Adversarial discriminative domain adaptation. In CVPR. 7167–7176.
  47. Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR 9, 11 (2008).
  48. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
  49. Deep hashing network for unsupervised domain adaptation. In CVPR. 5018–5027.
  50. Simplifying graph convolutional networks. In ICML. PMLR, 6861–6871.
  51. Non-IID Transfer Learning on Graphs. arXiv preprint arXiv:2212.08174 (2022).
  52. Unsupervised domain adaptive graph convolutional networks. In Proceedings of The Web Conference 2020. 1457–1467.
  53. A comprehensive survey on graph neural networks. TNNLS 32, 1 (2020), 4–24.
  54. Topology attack and defense for graph neural networks: An optimization perspective. arXiv preprint arXiv:1906.04214 (2019).
  55. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).
  56. Exploiting the intrinsic neighborhood structure for source-free domain adaptation. NIPS 34 (2021), 29393–29405.
  57. Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 460–470.
  58. Graph convolutional neural networks for web-scale recommender systems. In KDD. 974–983.
  59. Graph Domain Adaptation via Theory-Grounded Spectral Regularization. In ICLR.
  60. Central moment discrepancy (cmd) for domain-invariant representation learning. arXiv preprint arXiv:1702.08811 (2017).
  61. Robust unsupervised domain adaptation for neural networks via moment alignment. Information Sciences 483 (2019), 174–191.
  62. Domain adaptation under target and conditional shift. In ICML. PMLR, 819–827.
  63. Adversarial separation network for cross-network node classification. In CIKM. 2618–2626.
  64. Xiang Zhang and Marinka Zitnik. 2020. Gnnguard: Defending graph neural networks against adversarial attacks. NIPS 33 (2020), 9263–9275.
  65. AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation. arXiv preprint arXiv:2304.12566 (2023).
  66. H2mn: Graph similarity learning with hierarchical hypergraph matching networks. In KDD. 2274–2284.
  67. Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning. arXiv preprint arXiv:2211.06612 (2022).
  68. ANRL: attributed network representation learning via deep neural networks.. In Ijcai, Vol. 18. 3155–3161.
  69. Graph neural networks: A review of methods and applications. AI open 1 (2020), 57–81.
  70. Transfer learning of graph neural networks with ego-graph information maximization. NIPS 34 (2021), 1766–1779.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Zhen Zhang (384 papers)
  2. Meihan Liu (6 papers)
  3. Anhui Wang (1 paper)
  4. Hongyang Chen (61 papers)
  5. Zhao Li (109 papers)
  6. Jiajun Bu (52 papers)
  7. Bingsheng He (105 papers)
Citations (5)
View on Semantic Scholar

Summary

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

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