SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.22844 · NeurIPS · 2024

Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation

Huawei Shen, Qi Cao, Xueqi Cheng, Fei Sun, Kaike Zhang, Yunfan Wu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
Kaike-Zhang/PamaCF — 1 of 4
FunctionStatusWhere it lives
batch_split Ran Kaike-Zhang/PamaCF/utls/trainer.py
pointer only (licence: NONE) · get_code("6e95768bb4c4e402")
BasicTrainer Not yet run Kaike-Zhang/PamaCF/utls/trainer.py
pointer only (licence: NONE) · get_code("f7bdc1f79ad55ddf")
CFTrainer Not yet run Kaike-Zhang/PamaCF/utls/trainer.py
pointer only (licence: NONE) · get_code("c5e9acf41755b429")
PamaCFCFTrainer Not yet run Kaike-Zhang/PamaCF/utls/trainer.py
pointer only (licence: NONE) · get_code("ba68eb8891f7afcc")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.22844")
get_code_for_paper("2410.22844")
have("2410.22844")

Connect an agent — have() is free.