{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:56:51Z","timestamp":1773802611879,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"19","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>While deep learning (DL) has demonstrated significant success in recommender systems, it suffers from high computational complexity and poor scalability. In this work, we demonstrate, from an information-theoretic perspective, the redundancy of existing DL-based recommender models in two aspects: (1) Feature Redundancy. We show that many features are highly mutually correlated, noisy, or weakly predictive of user-item interaction labels. (2) Structural Redundancy. We further show that a large proportion of parameters in the dense layers contribute minimally to overall performance, indicating significant redundancy within the model architecture. To address these challenges, we propose REACTION (paRameter-Efficient LeArning for recommendaTION), an information-theoretic framework designed to reduce model complexity without sacrificing performance. REACTION consists of two core components: Adaptive Feature Extraction (AFE) leverages mutual information to  project high-dimensional sparse features into a compact, informative subspace. This adaptively filters noisy or weak features, reduces embedding parameters, and preserves implicit feature interactions without explicit high-order computation. \nDynamic Tower Fusion (DTF) bridges the representational gap between dual-tower expressiveness and single-tower efficiency. It facilitates rich cross-tower interactions during training, then merges the towers into a unified, low-latency single tower for inference. \nExtensive experiments on four large-scale benchmarks demonstrate that REACTION not only outperforms existing methods in accuracy but also achieves a drastic reduction in both model parameters and inference costs, thus establishing a new paradigm for efficient and scalable recommendation systems.<\/jats:p>","DOI":"10.1609\/aaai.v40i19.38631","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:42:40Z","timestamp":1773794560000},"page":"15977-15985","source":"Crossref","is-referenced-by-count":0,"title":["REACTION: Parameter-Efficient Learning for Recommendation"],"prefix":"10.1609","volume":"40","author":[{"given":"Song-Li","family":"Wu","sequence":"first","affiliation":[]},{"given":"Zhaocheng","family":"Du","sequence":"additional","affiliation":[]},{"given":"Qinglin","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Zhenhua","family":"Dong","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38631\/42593","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38631\/42593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:42:45Z","timestamp":1773794565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38631"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i19.38631","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}