| アイテムタイプ |
学術雑誌論文 / Journal Article(1) |
| 公開日 |
2025-08-27 |
| タイトル |
|
|
タイトル |
Balancing Embedding Spectrum for Recommendation |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Recommender system |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
collaborative filtering |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
embedding collapse |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
embedding spectrum |
| 資源タイプ |
|
|
資源タイプ |
journal article |
| アクセス権 |
|
|
アクセス権 |
open access |
| 著者 |
Peng, Shaowen
Sugiyama, Kazunari
Liu, Xin
Mine, Tsunenori
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Modern recommender systems heavily rely on high-quality representations learned from high-dimensional sparse data. While significant efforts have been invested in designing powerful algorithms for extracting user preferences, the factors contributing to good representations have remained relatively unexplored. In this work, we shed light on an issue in the existing pairwise learning paradigm (i.e., embedding collapse), that the representations tend to span a subspace of the whole embedding space, leading to a suboptimal solution and reducing the model capacity. Specifically, we show that alignment of positive pairs is equivalent to a low-pass filter causing users and items to collapse to a constant vector. While negative sampling can partially mitigate this issue by acting as a high-pass filter to balance the spectrum, leading to an incomplete collapse.To tackle this issue, we present a novel learning paradigm DirectSpec, which directly optimizes the spectrum distribution to ensure that users and items effectively span the entire embedding space. We demonstrate that many self-supervised learning algorithms without explicit negative sampling can be considered as special cases of DirectSpec. Furthermore, we show that optimizing the spectrum inappropriately could also be detrimental to data representation, where the key lies in a dynamic balance between alignment of positive pairs and spectrum balancing. Finally, we propose an enhanced and practical implementation DirectSpec+ to balance the embedding spectrum more adaptively and effectively. We implement DirectSpec+ on two popular recommender models: matrix factorization and LightGCN. Our experimental results demonstrate its effectiveness and efficiency over competitive baselines. |
| 書誌情報 |
en : ACM Transactions on Recommender Systems
巻 3,
号 4,
p. 1-25,
ページ数 25,
発行日 2025-02-17
|
| 出版者 |
|
|
出版者 |
Association for Computing Machinery (ACM) |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
2770-6699 |
| 出版者版DOI |
|
|
関連タイプ |
isIdenticalTo |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1145/3718488 |
| 出版者版URI |
|
|
関連タイプ |
isIdenticalTo |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://dl.acm.org/doi/10.1145/3718488 |
| 権利 |
|
|
権利情報Resource |
https://creativecommons.org/licenses/by/4.0/ |
|
権利情報 |
© 2025 Copyright held by the owner/author(s). This work is under a Creative Commons Attribution 4.0 International License. |
| 著者版フラグ |
|
|
出版タイプ |
VoR |
| 助成情報 |
|
|
|
助成機関名 |
New Energy and Industrial Technology Development Organization (NEDO) |
|
|
研究課題番号 |
JPNP20017 |
|
|
研究課題名 |
Research and Development Project of the Enhanced Infrastructures for Post-5G Information and Communication Systems |
fulltext (1.1 MB)
