Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation

• URL: http://arxiv.org/abs/2410.22844v2
• Date: Sat, 02 Nov 2024 15:23:36 GMT
• Title: Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
• Authors: Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun, Huawei Shen, Xueqi Cheng,
• Abstract summary: Adversarial Collaborative Filtering (ACF) is widely recognized as an effective strategy for enhancing the robustness of recommender systems against poisoning attacks. Despite empirical successes, the theoretical understanding of ACF's effectiveness in terms of both performance and robustness remains unclear. We propose Personalized Magnitude Adversarial Collaborative Filtering (PamaCF)
• Score: 60.719158008403376
• License:
• Abstract: Adversarial Collaborative Filtering (ACF), which typically applies adversarial perturbations at user and item embeddings through adversarial training, is widely recognized as an effective strategy for enhancing the robustness of Collaborative Filtering (CF) recommender systems against poisoning attacks. Besides, numerous studies have empirically shown that ACF can also improve recommendation performance compared to traditional CF. Despite these empirical successes, the theoretical understanding of ACF's effectiveness in terms of both performance and robustness remains unclear. To bridge this gap, in this paper, we first theoretically show that ACF can achieve a lower recommendation error compared to traditional CF with the same training epochs in both clean and poisoned data contexts. Furthermore, by establishing bounds for reductions in recommendation error during ACF's optimization process, we find that applying personalized magnitudes of perturbation for different users based on their embedding scales can further improve ACF's effectiveness. Building on these theoretical understandings, we propose Personalized Magnitude Adversarial Collaborative Filtering (PamaCF). Extensive experiments demonstrate that PamaCF effectively defends against various types of poisoning attacks while significantly enhancing recommendation performance.

Related papers

• CF-KAN: Kolmogorov-Arnold Network-based Collaborative Filtering to Mitigate Catastrophic Forgetting in Recommender Systems [16.261654043738385]
  Collaborative filtering (CF) remains essential in recommender systems. We propose CF-KAN, a new CF method utilizing Kolmogorov-Arnold networks (KANs) By learning nonlinear functions on the edge level, KANs are more robust to the catastrophic forgetting problem than sparses.
  arXiv  Detail & Related papers  (2024-08-25T12:12:08Z)
• The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks [90.52808174102157]
  In safety-critical applications such as medical imaging and autonomous driving, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks. A notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. This study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks.
  arXiv  Detail & Related papers  (2024-05-14T18:05:19Z)
• How Does Message Passing Improve Collaborative Filtering? [49.019075781827034]
  Collaborative filtering (CF) has exhibited prominent results for recommender systems and been broadly utilized for real-world applications. Message passing helps CF methods in a manner akin to its benefits for graph-based learning tasks in general. We present Test-time Aggregation for CF, a test-time augmentation framework that only conducts message passing once at inference time.
  arXiv  Detail & Related papers  (2024-03-27T18:53:04Z)
• Securing Recommender System via Cooperative Training [78.97620275467733]
  We propose a general framework, Triple Cooperative Defense (TCD), which employs three cooperative models that mutually enhance data. Considering existing attacks struggle to balance bi-level optimization and efficiency, we revisit poisoning attacks in recommender systems. We put forth a Game-based Co-training Attack (GCoAttack), which frames the proposed CoAttack and TCD as a game-theoretic process.
  arXiv  Detail & Related papers  (2024-01-23T12:07:20Z)
• User-Specific Bicluster-based Collaborative Filtering: Handling Preference Locality, Sparsity and Subjectivity [1.0398909602421018]
  Collaborative Filtering (CF) is the most common approach to build Recommender Systems. We propose USBFC, a Biclustering-based CF approach that creates user-specific models from strongly coherent and statistically significant rating patterns. USBFC achieves competitive predictive accuracy against state-of-the-art CF methods.
  arXiv  Detail & Related papers  (2022-11-15T18:10:52Z)
• The effectiveness of factorization and similarity blending [0.0]
  Collaborative Filtering (CF) is a technique which allows to leverage past users' preferences data to identify behavioural patterns and exploit them to predict custom recommendations. We show that blending factorization-based and similarity-based approaches can lead to a significant error decrease (-9.4%) on stand-alone models. We propose a novel extension of a similarity model, SCSR, which consistently reduce the complexity of the original algorithm.
  arXiv  Detail & Related papers  (2022-09-16T13:11:27Z)
• Enhancing Collaborative Filtering Recommender with Prompt-Based Sentiment Analysis [4.123009513488148]
  Collaborative Filtering(CF) recommender is a crucial application in the online market and ecommerce. Existing methods address the data sparsity issue by applying token-level sentiment analysis that translate text review into sentiment scores as a complement of the user rating. This paper attempts to optimize the sentiment analysis with advanced NLP models including BERT and RoBERTa.
  arXiv  Detail & Related papers  (2022-07-19T21:04:31Z)
• Confounder Identification-free Causal Visual Feature Learning [84.28462256571822]
  We propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders. CICF models the interventions among different samples based on front-door criterion, and then approximates the global-scope intervening effect upon the instance-level interventions. We uncover the relation between CICF and the popular meta-learning strategy MAML, and provide an interpretation of why MAML works from the theoretical perspective.
  arXiv  Detail & Related papers  (2021-11-26T10:57:47Z)
• Causal Collaborative Filtering [50.22155187512759]
  Causal Collaborative Filtering is a framework for modeling causality in collaborative filtering and recommendation. We show that many traditional CF algorithms are actually special cases of CCF under simplified causal graphs. We propose a conditional intervention approach for $do$-operations so that we can estimate the user-item causal preference.
  arXiv  Detail & Related papers  (2021-02-03T04:16:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.