思而後薦：釋放序列推薦中的潛在推理能力

Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation

March 28, 2025

作者: Jiakai Tang, Sunhao Dai, Teng Shi, Jun Xu, Xu Chen, Wen Chen, Wu Jian, Yuning Jiang

cs.AI

摘要

序列推薦（SeqRec）旨在通過捕捉用戶歷史互動中的序列模式來預測下一個項目，在許多現實世界的推薦系統中扮演著至關重要的角色。然而，現有方法主要採用直接前向計算範式，其中序列編碼器的最終隱藏狀態作為用戶表示。我們認為，由於其有限的計算深度，這種推理範式難以建模用戶偏好的複雜演變特性，並且對長尾項目的理解不夠細緻，導致性能欠佳。為解決這一問題，我們提出了ReaRec，這是首個用於推薦系統的推理時計算框架，通過隱式的多步推理來增強用戶表示。具體而言，ReaRec自回歸地將序列的最後隱藏狀態輸入序列推薦器，同時引入特殊的推理位置嵌入，以將原始項目編碼空間與多步推理空間解耦。此外，我們提出了兩種輕量級的基於推理的學習方法，集成推理學習（ERL）和漸進推理學習（PRL），以進一步有效挖掘ReaRec的推理潛力。在五個公開的真實世界數據集和不同的SeqRec架構上進行的大量實驗證明了我們提出的ReaRec的通用性和有效性。值得注意的是，事後分析表明，ReaRec顯著提升了多個序列推薦骨幹的性能上限，提升幅度約為30\%-50\%。因此，我們相信這項工作可以為序列推薦的推理時計算開闢一條新的、有前景的研究方向。

English

Sequential Recommendation (SeqRec) aims to predict the next item by capturing sequential patterns from users' historical interactions, playing a crucial role in many real-world recommender systems. However, existing approaches predominantly adopt a direct forward computation paradigm, where the final hidden state of the sequence encoder serves as the user representation. We argue that this inference paradigm, due to its limited computational depth, struggles to model the complex evolving nature of user preferences and lacks a nuanced understanding of long-tail items, leading to suboptimal performance. To address this issue, we propose ReaRec, the first inference-time computing framework for recommender systems, which enhances user representations through implicit multi-step reasoning. Specifically, ReaRec autoregressively feeds the sequence's last hidden state into the sequential recommender while incorporating special reasoning position embeddings to decouple the original item encoding space from the multi-step reasoning space. Moreover, we introduce two lightweight reasoning-based learning methods, Ensemble Reasoning Learning (ERL) and Progressive Reasoning Learning (PRL), to further effectively exploit ReaRec's reasoning potential. Extensive experiments on five public real-world datasets and different SeqRec architectures demonstrate the generality and effectiveness of our proposed ReaRec. Remarkably, post-hoc analyses reveal that ReaRec significantly elevates the performance ceiling of multiple sequential recommendation backbones by approximately 30\%-50\%. Thus, we believe this work can open a new and promising avenue for future research in inference-time computing for sequential recommendation.