Revisiting Collaborative Filtering by Unleashing the Power of Similarity
sigir26-082 · Full research paper · Moran Li, Xiaohe Yue, Chen Chen, M. X. Li, Yongqi Liu, Kaiqiao Zhan
Graph Neural Network Architectures f · 100%
Abstract
While deep learning-based approaches dominate the research on collaborative filtering (CF) in recommender systems, recent studies have re-examined this paradigm and found that deep models do not consistently outperform traditional CF alternatives on standard evaluation metrics. Notably, similarity-based methods exhibit substantial advantages. Inspired by these observations, we demonstrate that the performance of a minimalist similarity-based model can match or exceed leading CF approaches, highlighting its significant potential. Despite this, the expressiveness of high-performing similarity-based models is fundamentally confined to pairwise interactions within immediate neighborhoods, overlooking the combinatorial preference patterns in high-order connections. To overcome these limitations and fully unleash the potential of similarity-based models, we propose a novel bidirectional extension framework that systematically generalizes the modeling of similarity to group-level and multi-hop perspectives. However, directly computing these generalized similarities is prohibitively expensive due to their combinatorial complexity. To address this, we develop a MinHash-based estimation algorithm, which ensures the feasibility of the computation and reduces the complexity from exponential to linear. Extensive experiments on three public datasets show that our framework achieves competitive or superior performance over strong baselines, yielding relative improvements ranging from 4% to 11% on key metrics, underscoring the enduring power of similarity-based methods in recommender systems.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Riwei Lai | 49 | 71 Multi-Faceted Global Item Relation Learning for Session-Based Recommendation (2022) Graph-Based Sequential and Session Recommendation 55 Matryoshka Representation Learning for Recommendation with Layer- and Hardness-Adaptive Negative Sampling (2026) Negative Sampling and Loss Functions 55 Augmented Negative Sampling for Collaborative Filtering (2023) Negative Sampling and Loss Functions |
|
| 2 | Gyuseok Lee | 39 | 48 Continual Collaborative Distillation for Recommender System (2024) Efficient and Lightweight Graph Collaborative Filtering 45 Capturing User Interests from Data Streams for Continual Sequential Recommendation (2026) Efficient Sequential Recommendation Architectures 24 Harmonic Dataset Distillation for Time Series Forecasting (2026) Others |
Area chair
| Area chair | Match | |
|---|---|---|
| Xin Xin 0003 | 45 |
Area-chair candidates (6)
| Xin Xin 0003 assigned | 45 | 10 papers | |
| Yankai Chen 0001 | 41 | 6 papers | |
| Yanan Niu | 41 | 15 papers | |
| Leyu Lin | 40 | 15 papers | |
| Maolin Wang 0001 | 39 | 15 papers | |
| Kun Gai COI: co-author | 38 | 5 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Riwei Lai assigned | 49 | 3 | 71 Multi-Faceted Global Item Relation Learning for Session-Based Recommendation (2022) Graph-Based Sequential and Session Recommendation 55 Matryoshka Representation Learning for Recommendation with Layer- and Hardness-Adaptive Negative Sampling (2026) Negative Sampling and Loss Functions |
|
| 2 | Yongjing Hao | 46 | 3 | 67 How Do Graph Signals Affect Recommendation: Unveiling the Mystery of Low and High-Frequency Graph Signals (2026) Graph-based User and Item Representation Learning 67 A General Strategy Graph Collaborative Filtering for Recommendation Unlearning (2024) Graph Neural Network Architectures for CF |
|
| 3 | Jin Chen 0008 | 45 | 3 | 55 Ranking-Based Implicit Regularization for One-Class Collaborative Filtering (2022) Negative Sampling and Loss Functions 50 Automated Sparse and Low-Rank Shallow Autoencoders for Recommendation (2025) Efficient and Lightweight Graph Collaborative Filtering |
|
| 5 | Xiaolong Liu 0012 | 44 | 3 | 100 Unified Pretraining for Recommendation via Task Hypergraphs (2024) Graph Neural Network Architectures for CF 67 DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation (2023) Graph-based User and Item Representation Learning |
|
| 6 | Seongmin Park 0002 | 44 | 3 | 55 Toward a Better Understanding of Loss Functions for Collaborative Filtering (2023) Negative Sampling and Loss Functions 53 Linear Item-Item Models with Neural Knowledge for Session-based Recommendation (2025) Efficient and Long-Sequence Sequential Recommendation |
|
| 7 | Noveen Sachdeva | 42 | 3 | 69 ECLARE: Extreme Classification with Label Graph Correlations (2021) Graph Neural Network Architectures for CF 49 Sequential Variational Autoencoders for Collaborative Filtering (2019) Generative Models for Recommendation and Content › Others |
|
| 10 | Chen Wang 0052 | 40 | 3 | 68 Unified Pretraining for Recommendation via Task Hypergraphs (2024) Graph Pretraining and Foundation Models 49 Confidence-Aware Fine-Tuning of Sequential Recommendation Systems Via Conformal Prediction (2025) Contrastive and Self-Supervised Sequential Recommendation |
|
| 11 | Lantao Hu COI: co-author | 40 | 3 | 45 Soft Contrastive Sequential Recommendation (2024) Contrastive and Self-Supervised Sequential Recommendation 44 Modeling User Fatigue for Sequential Recommendation (2024) Contrastive and Self-Supervised Sequential Recommendation |
|
| 13 | Jieming Zhu | 40 | 3 | 48 FANS: Fast Non-Autoregressive Sequence Generation for Item List Continuation (2023) Efficient and Long-Sequence Sequential Recommendation 47 Cross-Batch Negative Sampling for Training Two-Tower Recommenders (2021) Negative Sampling and Loss Functions |
|
| 14 | Min Hou 0004 | 40 | 3 | 70 STGCN: A Spatial-Temporal Aware Graph Learning Method for POI Recommendation (2020) Graph Neural Network Architectures for CF 47 Mitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective (2025) Contrastive and Self-Supervised Sequential Recommendation |
|
| 15 | Zhengyi Yang 0007 | 40 | 3 | 47 A Generic Learning Framework for Sequential Recommendation with Distribution Shifts (2023) Contrastive and Self-Supervised Sequential Recommendation 41 On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders (2025) Diffusion and Flow Recommenders |
|
| 16 | Ke Wang 0038 | 40 | 3 | 46 Learning Aspect-Aware High-Order Representations from Ratings and Reviews for Recommendation (2023) Graph Learning for Text-Attributed and Heterogeneous Networks 43 Contrastive Multi-view Interest Learning for Cross-domain Sequential Recommendation (2024) Contrastive and Self-Supervised Sequential Recommendation |
|
| 18 | Jiancan Wu | 39 | 3 | 67 Graph convolution machine for context-aware recommender system (2022) Graph-based User and Item Representation Learning 44 Graph Contrastive Learning With Negative Propagation for Recommendation (2024) Graph Contrastive and Self-Supervised Learning |
|
| 19 | Hao Liu 0078 | 39 | 3 | 47 Mitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective (2025) Contrastive and Self-Supervised Sequential Recommendation 41 DA-DAN: A Dual Adversarial Domain Adaption Network for Unsupervised Non-overlapping Cross-domain Recommendation (2024) Domain Adaptation and Disentangled Representation for CDR |
|
| 20 | Xin Zhang 0091 | 39 | 3 | 66 Graph-aware collaborative reasoning for click-through rate prediction (2023) CTR and Conversion Rate Prediction 40 Deep Dynamic Interest Learning With Session Local and Global Consistency for Click-Through Rate Predictions (2022) CTR and Conversion Rate Prediction |
|
| 21 | Wei Guo 0006 | 39 | 3 | 50 Compressed Interaction Graph based Framework for Multi-behavior Recommendation (2023) Sequential and Session-Based Graph Recommendation 48 Breaking the Bottleneck: User-Specific Optimization and Real-Time Inference Integration for Sequential Recommendation (2025) Efficient and Long-Sequence Sequential Recommendation |
|
| 22 | Gyuseok Lee assigned | 39 | 3 | 48 Continual Collaborative Distillation for Recommender System (2024) Efficient and Lightweight Graph Collaborative Filtering 45 Capturing User Interests from Data Streams for Continual Sequential Recommendation (2026) Efficient Sequential Recommendation Architectures |
|
| 23 | Fei Sun 0001 | 39 | 3 | 49 Contrastive Learning for Sequential Recommendation (2022) Contrastive and Self-Supervised Sequential Recommendation 45 Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems (2024) Robustness to Noise and Distribution Shift |
|
| 24 | Bo Peng 0009 | 39 | 3 | 48 M2: Mixed Models With Preferences, Popularities and Transitions for Next-Basket Recommendation (2023) Efficient and Long-Sequence Sequential Recommendation 43 eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data (2024) Efficiency and Deployment |
|
| 25 | Lingling Yi | 39 | 3 | 49 Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation (2025) Sequential and Session-Based Graph Recommendation 48 Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filtering (2023) Efficient and Lightweight Graph Collaborative Filtering |
|
| 26 | Jianling Wang | 39 | 3 | 55 Improving Top-K Recommendation via JointCollaborative Autoencoders (2019) Negative Sampling and Loss Functions 49 Learning to Augment for Casual User Recommendation (2022) Contrastive and Self-Supervised Sequential Recommendation |
|
| 27 | Yimeng Bai | 39 | 3 | 45 GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting (2024) Multi-Task and Multi-Objective Optimization 42 Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework (2023) Recommendation Systems and Evaluation |
|
| 28 | Yongxin Ni | 39 | 3 | 55 Factored heterogeneous similarity model for recommendation with implicit feedback (2021) Negative Sampling and Loss Functions 55 Collaborative filtering with implicit feedback via learning pairwise preferences over user-groups and item-sets (2022) Negative Sampling and Loss Functions |
|
| 29 | Jizhi Zhang | 39 | 3 | 48 On the Theories Behind Hard Negative Sampling for Recommendation (2023) Recommendation Systems and Evaluation 43 BSL: Understanding and Improving Softmax Loss for Recommendation (2024) Popularity Bias and Debiasing in Recommendation |
|
| 30 | Lianghao Xia | 39 | 3 | 55 Self-Supervised Hypergraph Transformer for Recommender Systems (2022) Graph Contrastive and Self-Supervised Learning 41 Automated Self-Supervised Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning |
|
| 31 | Lichan Hong | 38 | 3 | 45 DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning (2021) Multi-Task and Multi-Objective Optimization 45 Co-optimize Content Generation and Consumption in a Large Scale Video Recommendation System (2024) Multi-Task and Multi-Objective Optimization |
|
| 32 | Bowen Zheng 0005 | 38 | 3 | 42 Towards a More User-Friendly and Easy-to-Use Benchmark Library for Recommender Systems (2023) Recommendation Systems and Evaluation 41 Enhancing Graph Contrastive Learning with Reliable and Informative Augmentation for Recommendation (2025) Graph Contrastive and Self-Supervised Learning |
|
| 33 | Qijiong Liu | 38 | 3 | 48 FANS: Fast Non-Autoregressive Sequence Generation for Item List Continuation (2023) Efficient and Long-Sequence Sequential Recommendation 47 Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector Quantization (2024) Item Tokenization and Semantic IDs |
|
| 34 | Hao Deng 0011 | 38 | 3 | 41 CSMF: Cascaded Selective Mask Fine-Tuning for Multi-Objective Embedding-Based Retrieval (2025) Multi-Task and Multi-Objective Optimization 40 REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems (2026) Item Tokenization and Semantic IDs |
|
| 35 | Yi Zhang 0103 | 38 | 3 | 56 Revisiting Graph-based Recommender Systems from the Perspective of Variational Auto-Encoder (2023) Graph-based User and Item Representation Learning 43 Simplify to the Limit! Embedding-Less Graph Collaborative Filtering for Recommender Systems (2025) Graph Contrastive and Self-Supervised Learning |