Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System

• URL: http://arxiv.org/abs/2506.00828v1
• Date: Sun, 01 Jun 2025 04:23:06 GMT
• Title: Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System
• Authors: Chao Wang, Yue Zheng, Yujing Zhang, Yan Feng, Zhe Wang, Xiaowei Shi, An You, Yu Chen,
• Abstract summary: In a single-slot recommendation system, users are only exposed to one item at a time, and the system cannot collect user feedback on multiple items simultaneously.<n>This paper introduces the Breaker model, which integrates an auxiliary task of user representation clustering with a multi-tower structure for cluster-specific preference modeling.<n>It has already been deployed and is actively serving tens of millions of users daily on Meituan, one of the most popular e-commerce platforms for services.
• Score: 20.933282101797214
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In a single-slot recommendation system, users are only exposed to one item at a time, and the system cannot collect user feedback on multiple items simultaneously. Therefore, only pointwise modeling solutions can be adopted, focusing solely on modeling the likelihood of clicks or conversions for items by users to learn user-item preferences, without the ability to capture the ranking information among different items directly. However, since user-side information is often much more abundant than item-side information, the model can quickly learn the differences in user intrinsic tendencies, which are independent of the items they are exposed to. This can cause these intrinsic tendencies to become a shortcut bias for the model, leading to insufficient mining of the most concerned user-item preferences. To solve this challenge, we introduce the Breaker model. Breaker integrates an auxiliary task of user representation clustering with a multi-tower structure for cluster-specific preference modeling. By clustering user representations, we ensure that users within each cluster exhibit similar characteristics, which increases the complexity of the pointwise recommendation task on the user side. This forces the multi-tower structure with cluster-driven parameter learning to better model user-item preferences, ultimately eliminating shortcut biases related to user intrinsic tendencies. In terms of training, we propose a delayed parameter update mechanism to enhance training stability and convergence, enabling end-to-end joint training of the auxiliary clustering and classification tasks. Both offline and online experiments demonstrate that our method surpasses the baselines. It has already been deployed and is actively serving tens of millions of users daily on Meituan, one of the most popular e-commerce platforms for services.

Related papers

• Retrieval Augmentation via User Interest Clustering [57.63883506013693]
  Industrial recommender systems are sensitive to the patterns of user-item engagement. We propose a novel approach that efficiently constructs user interest and facilitates low computational cost inference. Our approach has been deployed in multiple products at Meta, facilitating short-form video related recommendation.
  arXiv  Detail & Related papers  (2024-08-07T16:35:10Z)
• Recurrent Early Exits for Federated Learning with Heterogeneous Clients [22.429334632124817]
  Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clients with varying hardware capacities. We propose a recurrent early exit approach named ReeFL that fuses features from different sub-models into a single shared classifier.
  arXiv  Detail & Related papers  (2024-05-23T17:01:53Z)
• Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems [5.597511654202054]
  We show how to learn universal (i.e., supporting zero-shot adaptation without user or item auxiliary information) representations for nodes and edges from the bipartite user-item interaction graph.
  arXiv  Detail & Related papers  (2023-09-03T14:18:31Z)
• ClusterSeq: Enhancing Sequential Recommender Systems with Clustering based Meta-Learning [3.168790535780547]
  ClusterSeq is a Meta-Learning Clustering-Based Sequential Recommender System. It exploits dynamic information in the user sequence to enhance item prediction accuracy, even in the absence of side information. Our proposed approach achieves a substantial improvement of 16-39% in Mean Reciprocal Rank (MRR)
  arXiv  Detail & Related papers  (2023-07-25T18:53:24Z)
• The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm [154.47590401735323]
  Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems. This paper focuses on a challenging scenario where a user has multiple categories of interests. We propose a novel method called textitDiversity-Promoting Collaborative Metric Learning (DPCML)
  arXiv  Detail & Related papers  (2022-09-30T08:02:18Z)
• Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation [56.12499090935242]
  This work proposes a Knowledge-Enhanced Hierarchical Graph Transformer Network (KHGT) to investigate multi-typed interactive patterns between users and items in recommender systems. KHGT is built upon a graph-structured neural architecture to capture type-specific behavior characteristics. We show that KHGT consistently outperforms many state-of-the-art recommendation methods across various evaluation settings.
  arXiv  Detail & Related papers  (2021-10-08T09:44:00Z)
• Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling [9.639497198579257]
  deep learning is widely used to mine expressive tags to describe users' preferences from their historical actions. Traditional solutions usually introduce multiple independent Two-Tower models to mine tags from different actions. This paper introduces a novel multi-task model called Mixture of Virtual- Kernel Experts (MVKE) to learn multiple topic-related user preferences.
  arXiv  Detail & Related papers  (2021-06-04T07:52:52Z)
• Overcoming Data Sparsity in Group Recommendation [52.00998276970403]
  Group recommender systems should be able to accurately learn not only users' personal preferences but also preference aggregation strategy. In this paper, we take Bipartite Graphding Model (BGEM), the self-attention mechanism and Graph Convolutional Networks (GCNs) as basic building blocks to learn group and user representations in a unified way.
  arXiv  Detail & Related papers  (2020-10-02T07:11:19Z)
• PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest [54.56236567783225]
  PinnerSage is an end-to-end recommender system that represents each user via multi-modal embeddings. We conduct several offline and online A/B experiments to show that our method significantly outperforms single embedding methods.
  arXiv  Detail & Related papers  (2020-07-07T17:13:20Z)
• Multi-Center Federated Learning [62.57229809407692]
  This paper proposes a novel multi-center aggregation mechanism for federated learning. It learns multiple global models from the non-IID user data and simultaneously derives the optimal matching between users and centers. Our experimental results on benchmark datasets show that our method outperforms several popular federated learning methods.
  arXiv  Detail & Related papers  (2020-05-03T09:14:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.