Lune

WWW2024Top-tier venue

UnifiedSSR: A Unified Framework of Sequential Search and Recommendation

Jiayi Xie, Shang Liu, Gao Cong, Zhenzhong Chen

Abstract

In this work, we propose a Unified framework of Sequential Search and Recommendation (UnifiedSSR) for joint learning of user behavior history in both search and recommendation scenarios. Specifically, we consider user-interacted products in the recommendation scenario, as well as user-interacted products and user-issued queries in the search scenario as three distinct types of user behaviors. We propose a dual-branch network to encode the pair of interacted product history and issued query history in the search scenario in parallel. This allows for cross-scenario modeling by deactivating the query branch for the recommendation scenario. Through the parameter sharing between dual branches, as well as between product branches in two scenarios, we incorporate cross-view and cross-scenario associations of user behaviors, providing a comprehensive understanding of user behavior patterns. To further enhance user behavior modeling by capturing the underlying dynamic intent, an Intent-oriented Session Modeling module is designed for inferring intent-oriented semantic sessions from the contextual information in behavior sequences. In particular, we consider self-supervised learning signals from two perspectives for intent-oriented semantic session locating, which encourage session discrimination within each behavior sequence and session alignment between dual behavior sequences. Extensive experiments on three public datasets demonstrate that UnifiedSSR consistently outperforms state-of-the-art methods for both search and recommendation.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Debiased Contrastive Learning for Sequential Recommendation cites Intent Contrastive Learning for Sequential Recommendation
  • Debiased Contrastive Learning for Sequential Recommendation cites Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
  • MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment cites UniSAR: Modeling User Transition Behaviors between Search and Recommendation
  • MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment cites Filter-enhanced MLP is All You Need for Sequential Recommendation
  • Unifying Search and Recommendation in LLMs via Gradient Multi-Subspace Tuning cites UniSAR: Modeling User Transition Behaviors between Search and Recommendation
  • UniSAR: Modeling User Transition Behaviors between Search and Recommendation cites Intent Contrastive Learning for Sequential Recommendation
  • UniSAR: Modeling User Transition Behaviors between Search and Recommendation cites Filter-enhanced MLP is All You Need for Sequential Recommendation
  • Dual-Horizon Interest Model for Unified Search and Recommendation cites Intent Contrastive Learning for Sequential Recommendation
  • Dual-Horizon Interest Model for Unified Search and Recommendation cites UniSAR: Modeling User Transition Behaviors between Search and Recommendation
  • Dual-Horizon Interest Model for Unified Search and Recommendation cites Filter-enhanced MLP is All You Need for Sequential Recommendation
  • Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search cites MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment
  • Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search cites UniSAR: Modeling User Transition Behaviors between Search and Recommendation
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. UniSAR: Modeling User Transition Behaviors between Search and RecommendationTeng Shi, Zihua Si, Jun Xu, Xiao Zhang et al.SIGIR 2024 · 16 citations
  2. MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation AlignmentWeicong Qin, Yi Xu, Weijie Yu, Chenglei Shen et al.ACL 2025 · 7 citations
  3. Unifying Search and Recommendation in LLMs via Gradient Multi-Subspace TuningJujia Zhao, Zihan Wang, Shuaiqun Pan, Suzan Verberne et al.SIGIR 2026 · 1 citation
  4. Dual-Horizon Interest Model for Unified Search and RecommendationWenhao Zhu, Yuxin Li, Shuo Wang, Hao WangAAAI 2026
  5. Similarity = Value? Consultation Value-Assessment and Alignment for Personalized SearchWeicong Qin, Yi Xu, Weijie Yu, Teng Shi et al.EMNLP 2025

Builds on12

  1. Intent Contrastive Learning for Sequential RecommendationYongjun Chen, Zhiwei Liu, Jia Li, Julian J. McAuley et al.WWW 2022 · 429 citations
  2. Filter-enhanced MLP is All You Need for Sequential RecommendationKun Zhou, Hui Yu, Wayne Xin Zhao, Ji-Rong WenWWW 2022 · 411 citations
  3. Debiased Contrastive Learning for Sequential RecommendationYuhao Yang, Chao Huang, Lianghao Xia, Chunzhen Huang et al.WWW 2023 · 199 citations
  4. Multi-Behavior Hypergraph-Enhanced Transformer for Sequential RecommendationYuhao Yang, Chao Huang, Lianghao Xia, Yuxuan Liang et al.KDD 2022 · 165 citations
  5. DPT: Deformable Patch-based Transformer for Visual RecognitionZhiyang Chen, Yousong Zhu, Chaoyang Zhao, Guosheng Hu et al.ACM MM 2021 · 118 citations

Related papers

  1. When Search Meets Recommendation: Learning Disentangled Search Representation for RecommendationZihua Si, Zhongxiang Sun, Xiao Zhang, Jun Xu et al.SIGIR 2023 · 29 citations
  2. Micro-Behavior Encoding for Session-based RecommendationJiahao Yuan, Wendi Ji, Dell Zhang, Jinwei Pan et al.ICDE 2022 · 15 citations
  3. Mining Informative Interests via Latent Cross Reasoning for Search Enhanced RecommendationTeng Shi, Weicong Qin, Weijie Yu, Xiao Zhang et al.SIGIR 2026
  4. Learning from the Wisdom of Crowds: Exploiting Similar Sessions for Session SearchYuhang Ye, Zhonghua Li, Zhicheng Dou, Yutao Zhu et al.AAAI 2023 · 4 citations
  5. Self-Supervised Dual-Channel Attentive Network for Session-based Social RecommendationLiuyin Wang, Xianghong Xu, Kai Ouyang, Huanzhong Duan et al.ICDE 2022 · 22 citations
Dusk over the sea between two cliffs drawn in fine vertical lines