Summary of Multi-modal Recommendation Unlearning For Legal, Licensing, and Modality Constraints, by Yash Sinha et al.
Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints
by Yash Sinha, Murari Mandal, Mohan Kankanhalli
First submitted to arxiv on: 24 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper focuses on developing methods for multi-modal recommender systems (MMRS) that prioritize user privacy. The authors address the issue of unlearning private user data from uni-modal recommender systems (RS), which has become increasingly important in today’s data-driven world. They also explore ways to remove outdated item preferences, revoked licenses, and legally requested content removals from MMRS models. To achieve this, they propose novel methods that leverage graph-based techniques to efficiently update the user-item interaction graphs. The proposed approach is designed to balance the trade-off between recommendation accuracy and user privacy, ensuring that sensitive information is not inadvertently disclosed. By doing so, the authors aim to provide a more comprehensive understanding of how MMRS can be adapted to meet the rising demands for data privacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores ways to make multi-modal recommender systems (MMRS) more private and responsible. Right now, these systems are great at suggesting things like products or social media posts based on what people have liked in the past. But with so many people worried about their personal data being shared without permission, we need new ways to remove old preferences that are no longer relevant or should be taken down. This paper looks at how we can do this while still making good recommendations. |
Keywords
» Artificial intelligence » Multi modal
