Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Mining Stable Preferences: Adaptive Modality Decorrelation for Multimedia Recommendation (2306.14179v1)

Published 25 Jun 2023 in cs.IR, cs.AI, and cs.LG

Abstract: Multimedia content is of predominance in the modern Web era. In real scenarios, multiple modalities reveal different aspects of item attributes and usually possess different importance to user purchase decisions. However, it is difficult for models to figure out users' true preference towards different modalities since there exists strong statistical correlation between modalities. Even worse, the strong statistical correlation might mislead models to learn the spurious preference towards inconsequential modalities. As a result, when data (modal features) distribution shifts, the learned spurious preference might not guarantee to be as effective on the inference set as on the training set. We propose a novel MOdality DEcorrelating STable learning framework, MODEST for brevity, to learn users' stable preference. Inspired by sample re-weighting techniques, the proposed method aims to estimate a weight for each item, such that the features from different modalities in the weighted distribution are decorrelated. We adopt Hilbert Schmidt Independence Criterion (HSIC) as independence testing measure which is a kernel-based method capable of evaluating the correlation degree between two multi-dimensional and non-linear variables. Our method could be served as a play-and-plug module for existing multimedia recommendation backbones. Extensive experiments on four public datasets and four state-of-the-art multimedia recommendation backbones unequivocally show that our proposed method can improve the performances by a large margin.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Permutation weighting. In ICML. PMLR, 331–341.
  2. Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019).
  3. Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention. In SIGIR. 335–344.
  4. Peng Cui and Susan Athey. 2022. Stable learning establishes some common ground between causal inference and machine learning. Nature Machine Intelligence 4, 2 (2022), 110–115.
  5. MV-RNN: A multi-view recurrent neural network for sequential recommendation. IEEE Transactions on Knowledge and Data Engineering 32, 2 (2018), 317–331.
  6. Recommender systems leveraging multimedia content. ACM Computing Surveys (CSUR) (2020).
  7. Invariant Representation Learning for Multimedia Recommendation. In ACM Multimedia.
  8. Generalizing Graph Neural Networks on Out-Of-Distribution Graphs. arXiv preprint arXiv:2111.10657 (2021).
  9. Kernel choice and classifiability for RKHS embeddings of probability distributions. Advances in neural information processing systems 22 (2009).
  10. Xavier Glorot and Yoshua Bengio. 2010. Understanding the Difficulty of Training Deep Feedforward Neural Networks. In AISTATS. 249–256.
  11. Daniel Greenfeld and Uri Shalit. 2020. Robust learning with the hilbert-schmidt independence criterion. In International Conference on Machine Learning. PMLR, 3759–3768.
  12. Measuring statistical dependence with Hilbert-Schmidt norms. In International conference on algorithmic learning theory. Springer, 63–77.
  13. A kernel statistical test of independence. Advances in neural information processing systems 20 (2007).
  14. Ruining He and Julian McAuley. 2016. VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback. In AAAI. 144–150.
  15. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. In SIGIR. 639–648.
  16. Visually-Aware Fashion Recommendation and Design with Generative Image Models. In ICDM. 207–216.
  17. MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation. In CIKM. 993–1002.
  18. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR.
  19. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.
  20. Stable prediction across unknown environments. In KDD. 1617–1626.
  21. Stable prediction with model misspecification and agnostic distribution shift. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 4485–4492.
  22. Hierarchical fashion graph network for personalized outfit recommendation. In SIGIR. 159–168.
  23. Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation. arXiv preprint arXiv:2304.05615 (2023).
  24. DeepStyle: Learning User Preferences for Visual Recommendation. In SIGIR. 841–844.
  25. Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation. In CIKM. 1099–1108.
  26. Multi-trends Enhanced Dynamic Micro-video Recommendation. arXiv preprint arXiv:2110.03902 (2021).
  27. Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017).
  28. Deep stable representation learning on electronic health records. arXiv preprint arXiv:2209.01321 (2022).
  29. Image-Based Recommendations on Styles and Substitutes. In SIGIR. 43–52.
  30. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In EMNLP. 3980–3990.
  31. BPR: Bayesian Personalized Ranking from Implicit Feedback. In UAI. 452–461.
  32. Recommendations as treatments: Debiasing learning and evaluation. In ICML. PMLR, 1670–1679.
  33. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision. 618–626.
  34. Stable learning via sample reweighting. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 5692–5699.
  35. Towards out-of-distribution generalization: A survey. arXiv preprint arXiv:2108.13624 (2021).
  36. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Workshop Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.).
  37. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017).
  38. Counterfactual explainable recommendation. In CIKM. 1784–1793.
  39. Graph Attention Networks. In ICLR.
  40. Neural Graph Collaborative Filtering. In SIGIR. 165–174.
  41. Invariant Preference Learning for General Debiasing in Recommendation. In KDD. 1969–1978.
  42. Unbiased sequential recommendation with latent confounders. In WWW. 2195–2204.
  43. Contrastive Learning for Cold-Start Recommendation. In ACM Multimedia.
  44. Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback. In ACM Multimedia. 3451–3459.
  45. MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video. In ACM Multimedia. 1437–1445.
  46. Session-based Recommendation with Graph Neural Networks. In AAAI. 346–353.
  47. Why Stable Learning Works? A Theory of Covariate Shift Generalization. arXiv preprint arXiv:2111.02355 (2021).
  48. Why do we click: visual impression-aware news recommendation. In ACM Multimedia. 3881–3890.
  49. Mining Latent Structures for Multimedia Recommendation. In ACM Multimedia. 3872–3880.
  50. Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendation. IEEE Transactions on Knowledge and Data Engineering (2022).
  51. Dynamic graph neural networks for sequential recommendation. IEEE Transactions on Knowledge and Data Engineering (2022).
  52. Stable Prediction on Graphs with Agnostic Distribution Shift. arXiv preprint arXiv:2110.03865 (2021).
  53. CCL4Rec: Contrast over Contrastive Learning for Micro-video Recommendation. arXiv preprint arXiv:2208.08024 (2022).
  54. Deep stable learning for out-of-distribution generalization. In CVPR. 5372–5382.
  55. Deep Graph Structure Learning for Robust Representations: A Survey. arXiv.org (March 2021). arXiv:2103.03036v1 [cs.LG]
Citations (6)
View on Semantic Scholar

Summary

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

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