Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Sign-Guided Bipartite Graph Hashing for Hamming Space Search (2405.02716v1)

Published 4 May 2024 in cs.IR

Abstract: Bipartite graph hashing (BGH) is extensively used for Top-K search in Hamming space at low storage and inference costs. Recent research adopts graph convolutional hashing for BGH and has achieved the state-of-the-art performance. However, the contributions of its various influencing factors to hashing performance have not been explored in-depth, including the same/different sign count between two binary embeddings during Hamming space search (sign property), the contribution of sub-embeddings at each layer (model property), the contribution of different node types in the bipartite graph (node property), and the combination of augmentation methods. In this work, we build a lightweight graph convolutional hashing model named LightGCH by mainly removing the augmentation methods of the state-of-the-art model BGCH. By analyzing the contributions of each layer and node type to performance, as well as analyzing the Hamming similarity statistics at each layer, we find that the actual neighbors in the bipartite graph tend to have low Hamming similarity at the shallow layer, and all nodes tend to have high Hamming similarity at the deep layers in LightGCH. To tackle these problems, we propose a novel sign-guided framework SGBGH to make improvement, which uses sign-guided negative sampling to improve the Hamming similarity of neighbors, and uses sign-aware contrastive learning to help nodes learn more uniform representations. Experimental results show that SGBGH outperforms BGCH and LightGCH significantly in embedding quality.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. S. Kim, T. Lee, S. Hwang, and S. Elnikety, “List intersection for web search: Algorithms, cost models, and optimizations,” Proc. VLDB Endow., vol. 12, no. 1, pp. 1–13, 2018.
  2. J. Pound, S. Paparizos, and P. Tsaparas, “Facet discovery for structured web search: A query-log mining approach,” in SIGMOD, 2011, pp. 169–180.
  3. I. Antonellis, H. Garcia-Molina, and C. Chang, “Simrank++: query rewriting through link analysis of the click graph,” Proc. VLDB Endow., vol. 1, no. 1, pp. 408–421, 2008.
  4. S. Gurukar, N. Pancha, A. Zhai, E. Kim, S. Hu, S. Parthasarathy, C. Rosenberg, and J. Leskovec, “Multibisage: A web-scale recommendation system using multiple bipartite graphs at pinterest,” Proc. VLDB Endow., vol. 16, no. 4, pp. 781–789, 2022.
  5. Z. Li, X. Shen, Y. Jiao, X. Pan, P. Zou, X. Meng, C. Yao, and J. Bu, “Hierarchical bipartite graph neural networks: Towards large-scale e-commerce applications,” in ICDE, 2020, pp. 1677–1688.
  6. C. Eksombatchai, P. Jindal, J. Z. Liu, Y. Liu, R. Sharma, C. Sugnet, M. Ulrich, and J. Leskovec, “Pixie: A system for recommending 3+ billion items to 200+ million users in real-time,” in WWW, 2018, p. 1775–1784.
  7. R. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec, “Graph convolutional neural networks for web-scale recommender systems,” in SIGKDD, 2018, pp. 974–983.
  8. J. Wang, P. Huang, H. Zhao, Z. Zhang, B. Zhao, and D. L. Lee, “Billion-scale commodity embedding for e-commerce recommendation in alibaba,” in SIGKDD, 2018, pp. 839–848.
  9. J. Wang, T. Zhang, J. Song, N. Sebe, and H. T. Shen, “A survey on learning to hash,” TPAMI, vol. 40, no. 4, pp. 769–790, 2018.
  10. K. Zhou and H. Zha, “Learning binary codes for collaborative filtering,” in SIGKDD, 2012, pp. 498–506.
  11. Z. Zhang, Q. Wang, L. Ruan, and L. Si, “Preference preserving hashing for efficient recommendation,” in SIGIR, 2014, pp. 183–192.
  12. H. Liu, X. He, F. Feng, L. Nie, R. Liu, and H. Zhang, “Discrete factorization machines for fast feature-based recommendation,” in IJCAI, 2018, pp. 3449–3455.
  13. H. Zhang, F. Shen, W. Liu, X. He, H. Luan, and T.-S. Chua, “Discrete collaborative filtering,” in SIGIR, 2016, pp. 325–334.
  14. Y. Zhang, D. Lian, and G. Yang, “Discrete personalized ranking for fast collaborative filtering from implicit feedback,” in AAAI, 2017, pp. 1669–1675.
  15. Y. Xu, L. Zhu, Z. Cheng, J. Li, and J. Sun, “Multi-feature discrete collaborative filtering for fast cold-start recommendation,” in AAAI, 2020, pp. 270–278.
  16. X. Wang, X. He, M. Wang, F. Feng, and T.-S. Chua, “Neural graph collaborative filtering,” in SIGIR, 2019, pp. 165–174.
  17. X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang, “Lightgcn: Simplifying and powering graph convolution network for recommendation,” in SIGIR, 2020, pp. 639–648.
  18. J. Cao, X. Lin, S. Guo, L. Liu, T. Liu, and B. Wang, “Bipartite graph embedding via mutual information maximization,” in WSDM, 2021, pp. 635–643.
  19. L. Xia, C. Huang, and C. Zhang, “Self-supervised hypergraph transformer for recommender systems,” in SIGKDD, 2022, pp. 2100–2109.
  20. L. Xia, C. Huang, Y. Xu, J. Zhao, D. Yin, and J. Huang, “Hypergraph contrastive collaborative filtering,” in SIGIR, 2022, pp. 70–79.
  21. Y. Chen, H. Guo, Y. Zhang, C. Ma, R. Tang, J. Li, and I. King, “Learning binarized graph representations with multi-faceted quantization reinforcement for top-k recommendation,” in SIGKDD, 2022, pp. 168–178.
  22. Y. Chen, Y. Fang, Y. Zhang, and I. King, “Bipartite graph convolutional hashing for effective and efficient top-n search in hamming space,” in WWW, 2023, pp. 3164–3172.
  23. Q. Tan, N. Liu, X. Zhao, H. Yang, J. Zhou, and X. Hu, “Learning to hash with graph neural networks for recommender systems,” in WWW, 2020, pp. 1988–1998.
  24. H. Liu, Y. Wei, J. Yin, and L. Nie, “Hs-gcn: Hamming spatial graph convolutional networks for recommendation,” TKDE, vol. 35, no. 6, pp. 5977–5990, 2023.
  25. H. Wang, D. Lian, and Y. Ge, “Binarized collaborative filtering with distilling graph convolutional networks,” in IJCAI, 2019, pp. 4802–4808.
  26. X. Zhou, F. Shen, L. Liu, W. Liu, L. Nie, Y. Yang, and H. T. Shen, “Graph convolutional network hashing,” IEEE Trans. Cybern., vol. 50, no. 4, pp. 1460–1472, 2020.
  27. W.-C. Kang and J. McAuley, “Candidate generation with binary codes for large-scale top-n recommendation,” in CIKM, 2019, pp. 1523–1532.
  28. X. Zhou, D. Lin, Y. Liu, and C. Miao, “Layer-refined graph convolutional networks for recommendation,” in ICDE, 2023, pp. 1247–1259.
  29. Y. Xu, K. Han, C. Xu, Y. Tang, C. Xu, and Y. Wang, “Learning frequency domain approximation for binary neural networks,” in NeurIPS, 2021, pp. 25 553–25 565.
  30. S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme, “Bpr: Bayesian personalized ranking from implicit feedback,” in UAI, 2009, pp. 452–461.
  31. X. He, L. Liao, H. Zhang, L. Nie, X. Hu, and T.-S. Chua, “Neural collaborative filtering,” in WWW, 2017, pp. 173–182.
  32. J. Wu, X. Wang, F. Feng, X. He, L. Chen, J. Lian, and X. Xie, “Self-supervised graph learning for recommendation,” in SIGIR, 2021, pp. 726–735.
  33. J. Yu, H. Yin, X. Xia, T. Chen, L. Cui, and Q. V. H. Nguyen, “Are graph augmentations necessary? simple graph contrastive learning for recommendation,” in SIGIR, 2022, pp. 1294–1303.
  34. L. Van der Maaten and G. Hinton, “Visualizing data using t-sne,” JMLR, vol. 9, no. 11, 2008.
  35. Z. I. Botev, J. F. Grotowski, and D. P. Kroese, “Kernel density estimation via diffusion,” 2010.
  36. X. Wang, Y. Lin, and X. Li, “Cgat: Center-guided adversarial training for deep hashing-based retrieval,” in WWW, 2023, pp. 3268–3277.
  37. R.-C. Tu, X.-L. Mao, J.-N. Guo, W. Wei, and H. Huang, “Partial-softmax loss based deep hashing,” in WWW, 2021, pp. 2869–2878.
  38. J. Yu, X. Xia, T. Chen, L. Cui, N. Q. V. Hung, and H. Yin, “Xsimgcl: Towards extremely simple graph contrastive learning for recommendation,” TKDE, vol. 36, no. 2, pp. 913–926, 2024.
  39. X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” in AISTATS, 2010, pp. 249–256.
  40. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in ICLR, 2015.
  41. W. L. Hamilton, R. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” in NeurIPS, 2017, pp. 1025–1035.

Summary

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

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