Incremental Multi-Behavior Recommendation
sigir26-148 · Full research paper · Jiahao Gong, Weike Pan
Sequential and Session-Based Graph R · 50% Multi-Behavior Recommendation · 25% Multi-Task and Multi-Objective Optim · 12% Multi-Behavior Recommendation · 12%
Abstract
Multi-behavior recommendation, unlike traditional single-behavior recommendation focusing solely on the target behavior (e.g., purchase), exploits multiple types of user-item interactions (e.g., view, favorite, add-to-cart, purchase) to mitigate data sparsity and learn more comprehensive user preferences. However, real-world data is inherently transmitted in a streaming manner, and most existing multi-behavior recommendation models are trained on static offline datasets, which cannot efficiently handle continuously arriving data streams. Full retraining incurs high computational cost and long training time. In contrast, fine-tuning is efficient but prone to ''catastrophic forgetting'', resulting in performance degradation. Incremental recommendation techniques offer a potential solution, but the existing methods are mostly designed for cases with one single behavior, ignoring valuable information contained in heterogeneous behaviors. To fill this gap, we introduce a new and important problem, i.e., incremental multi-behavior recommendation (IMBR), requiring a model to handle streaming data while utilizing valuable heterogeneous behaviors. To this end, we propose a novel solution called Behavior-aware Incremental Graph Convolution Network with Multi-Task Learning (BIGCN-MTL) for IMBR. Specifically, our BIGCN-MTL contains two key modules: behavior-aware incremental graph convolution network (BIGCN), which employs incremental cascading graph convolution to preserve both historical neighborhood information and behavior cascading dependency, and historical interest distillation (HID), which maintains users' preference stability and prevents behavioral semantic forgetting via non-interest consistency constraint and preference contrastive distillation. Extensive experiments on four real-world datasets demonstrate that our BIGCN-MTL achieves superior recommendation performance and improves training efficiency compared to full retraining. The source code of our BIGCN-MTL is available at https://github.com/codingPeter1/BIGCN-MTL.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Yongjing Hao | 53 | 74 Edge-enhanced Global Disentangled Graph Neural Network for Sequential Recommendation (2023) Sequential and Session-Based Graph Recommendation 74 Multi-dimensional Graph Neural Network for Sequential Recommendation (2023) Sequential and Session-Based Graph Recommendation 59 Learnable Model Augmentation Contrastive Learning for Sequential Recommendation (2024) Contrastive and Self-Supervised Sequential Recommendation |
|
| 2 | Ziru Liu | 48 | 55 Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention (2024) Multi-Behavior and Multi-Interest Sequential Recommendation 55 Multi-Task Recommendations with Reinforcement Learning (2023) Offline RL for Recommendation 52 Modeling User Retention through Generative Flow Networks (2024) Multi-Behavior Recommendation |
Area chair
| Area chair | Match | |
|---|---|---|
| Yanan Niu | 59 |
Area-chair candidates (6)
| Yanan Niu assigned | 59 | 15 papers | |
| Xin Xin 0003 | 47 | 10 papers | |
| Weiming Liu 0005 | 45 | 8 papers | |
| Qiaoyu Tan | 45 | 7 papers | |
| Leyu Lin | 44 | 15 papers | |
| Kun Gai | 43 | 5 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 2 | Yongjing Hao assigned | 53 | 3 | 74 Edge-enhanced Global Disentangled Graph Neural Network for Sequential Recommendation (2023) Sequential and Session-Based Graph Recommendation 74 Multi-dimensional Graph Neural Network for Sequential Recommendation (2023) Sequential and Session-Based Graph Recommendation |
|
| 3 | Jianling Wang | 51 | 3 | 77 Next-item Recommendation with Sequential Hypergraphs (2020) Sequential and Session-Based Graph Recommendation 77 Session-based Recommendation with Hypergraph Attention Networks (2021) Sequential and Session-Based Graph Recommendation |
|
| 4 | Fei Sun 0001 | 50 | 3 | 84 Multi-Behavior Sequential Modeling with Transition-Aware Graph Attention Network for E-Commerce Recommendation (2026) Sequential and Session-Based Graph Recommendation 55 BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer (2019) Graph-Based Sequential and Session Recommendation |
|
| 5 | Yang Song 0008 | 50 | 3 | 74 Sequential Recommendation with Graph Neural Networks (2021) Sequential and Session-Based Graph Recommendation 63 Learning and Optimization of Implicit Negative Feedback for Industrial Short-video Recommender System (2023) Multi-Behavior and Multi-Interest Sequential Recommendation |
|
| 6 | Shuchang Liu 0001 | 49 | 3 | 55 Multi-Task Recommendations with Reinforcement Learning (2023) Offline RL for Recommendation 52 Stratified Expert Cloning for Retention-Aware Recommendation at Scale (2025) Multi-Behavior Recommendation |
|
| 7 | Bo Peng 0009 | 49 | 3 | 55 Modeling Sequences as Star Graphs to Address Over-Smoothing in Self-Attentive Sequential Recommendation (2024) Graph-Based Sequential and Session Recommendation 55 Intention enhanced mixed attentive model for session-based recommendation (2024) Graph-Based Sequential and Session Recommendation |
|
| 8 | Wei Guo 0006 | 48 | 3 | 84 Compressed Interaction Graph based Framework for Multi-behavior Recommendation (2023) Sequential and Session-Based Graph Recommendation 60 Multi-Behavior Sequential Transformer Recommender (2022) Multi-Behavior and Multi-Interest Sequential Recommendation |
|
| 9 | Ziru Liu assigned | 48 | 3 | 55 Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention (2024) Multi-Behavior and Multi-Interest Sequential Recommendation 55 Multi-Task Recommendations with Reinforcement Learning (2023) Offline RL for Recommendation |
|
| 10 | Chunyang Wang 0001 | 48 | 3 | 77 Graph Diffusion-Based Representation Learning for Sequential Recommendation (2024) Sequential and Session-Based Graph Recommendation 64 Learning Graph-based Disentangled Representations for Next POI Recommendation (2022) Sequential and Session-Based Graph Recommendation |
|
| 11 | Chen Wang 0052 | 48 | 3 | 55 Sequential Recommendation with Auxiliary Item Relationships via Multi-Relational Transformer (2022) Graph-Based Sequential and Session Recommendation 49 Cluster-Aware Item Prompt Learning for Session-Based Recommendation (2025) LLM-Enhanced Sequential Recommendation |
|
| 12 | Junwei Pan COI: co-author | 47 | 3 | 50 Multi-Sequence Attentive User Representation Learning for Side-information Integrated Sequential Recommendation (2024) Sequential Recommendation with Side and Multimodal Information 50 Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs (2025) Generative Recommendation and Item Tokenization |
|
| 14 | Mengyuan Jing | 47 | 3 | 66 Dual Contrastive Learning for Multi-Behavior Recommendation (2023) Graph Contrastive and Self-Supervised Learning 55 Recognizing Semantics-Consistent Subsequences for Sequential Recommendation (2023) Graph-Based Sequential and Session Recommendation |
|
| 15 | Lianghao Xia | 47 | 3 | 84 Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation (2022) Sequential and Session-Based Graph Recommendation 66 Multi-Relational Contrastive Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning |
|
| 16 | James Caverlee | 47 | 3 | 77 Next-item Recommendation with Sequential Hypergraphs (2020) Sequential and Session-Based Graph Recommendation 77 Session-based Recommendation with Hypergraph Attention Networks (2021) Sequential and Session-Based Graph Recommendation |
|
| 17 | Bo Chen 0023 | 46 | 3 | 100 Compressed Interaction Graph based Framework for Multi-behavior Recommendation (2023) Sequential and Session-Based Graph Recommendation 50 ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation (2024) Sequential and Session-based Recommendation |
|
| 18 | Yong He 0009 | 46 | 3 | 48 Mixture of Graph Enhanced Expert Networks for Multi-task Recommendation (2022) Multi-Task and Multi-Objective Optimization 48 MASR: A Model-Agnostic Sparse Routing Architecture for Arbitrary Order Feature Sharing in Multi-Task Learning (2022) Multi-Task and Multi-Objective Optimization |
|
| 19 | Huifeng Guo | 45 | 3 | 84 Compressed Interaction Graph based Framework for Multi-behavior Recommendation (2023) Sequential and Session-Based Graph Recommendation 46 FuXi-γ: Efficient Sequential Recommendation with Exponential-Power Temporal Encoder and Diagonal-Sparse Positional Mechanism (2026) Efficient Sequential Recommendation Architectures |
|
| 20 | Yimeng Bai | 45 | 3 | 48 GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting (2024) Multi-Task and Multi-Objective Optimization 44 Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework (2023) Recommendation Systems and Evaluation |
|
| 21 | Xuanhua Yang | 45 | 3 | 45 Towards Personalized Bundle Creative Generation with Contrastive Non-Autoregressive Decoding (2022) Diffusion and Flow Recommenders 45 Hierarchical User Long-term Behavior Modeling for Click-Through Rate Prediction (2025) CTR and Conversion Rate Prediction |
|
| 23 | Zhengyi Yang 0007 | 45 | 3 | 51 LLaRA: Large Language-Recommendation Assistant (2024) Sequential and Session-based Recommendation 45 Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion (2023) Diffusion and Flow Recommenders |
|
| 25 | Lingling Yi | 45 | 3 | 81 Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation (2025) Sequential and Session-Based Graph Recommendation 58 Item-Provider Co-learning for Sequential Recommendation (2022) Graph Contrastive and Self-Supervised Learning |
|
| 26 | Bowen Zheng 0005 | 44 | 3 | 52 Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation (2025) Sequential and Session-based Recommendation 50 Reciprocal Sequential Recommendation (2023) Sequential Recommendation with User Modeling and Profiling |
|
| 27 | Jinxin Hu | 44 | 3 | 50 CSMF: Cascaded Selective Mask Fine-Tuning for Multi-Objective Embedding-Based Retrieval (2025) Recommendation with Search and Ranking 50 SASNet: Stage-aware Sequential Matching for Online Travel Recommendation (2022) Sequential Recommendation with User Modeling and Profiling |
|
| 29 | Ed H. Chi | 44 | 3 | 48 Co-optimize Content Generation and Consumption in a Large Scale Video Recommendation System (2024) Multi-Task and Multi-Objective Optimization 48 DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning (2021) Multi-Task and Multi-Objective Optimization |
|
| 30 | Lichan Hong | 44 | 3 | 49 Improving Training Stability for Multitask Ranking Models in Recommender Systems (2023) Recommendation Systems and Evaluation 48 Co-optimize Content Generation and Consumption in a Large Scale Video Recommendation System (2024) Multi-Task and Multi-Objective Optimization |
|
| 31 | Hyunsik Yoo | 44 | 3 | 52 Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation (2026) Multi-Behavior and Multi-Interest Sequential Recommendation 51 Capturing User Interests from Data Streams for Continual Sequential Recommendation (2026) Efficient and Long-Sequence Sequential Recommendation |
|
| 32 | Jie Jiang 0015 COI: co-author | 44 | 3 | 52 HIT: Learning a Hierarchical Tree-Based Model with Variable-Length Layers for Recommendation Systems (2023) Efficient and Long-Sequence Sequential Recommendation 50 Multi-Sequence Attentive User Representation Learning for Side-information Integrated Sequential Recommendation (2024) Sequential Recommendation with Side and Multimodal Information |
|
| 33 | Lantao Hu | 44 | 3 | 48 Modeling User Fatigue for Sequential Recommendation (2024) Contrastive and Self-Supervised Sequential Recommendation 46 Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention (2024) Multi-Behavior and Multi-Interest Sequential Recommendation |
|
| 34 | Qiang Luo 0004 | 43 | 3 | 52 MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever (2025) Multi-Task and Multi-Objective Optimization 50 FIM: Frequency-Aware Multi-View Interest Modeling for Local-Life Service Recommendation (2025) Sequential Recommendation with User Modeling and Profiling |
|
| 36 | Seongmin Park 0002 | 43 | 3 | 51 Temporal Linear Item-Item Model for Sequential Recommendation (2025) Efficient and Long-Sequence Sequential Recommendation 50 MUFFIN: Mixture of User-Adaptive Frequency Filtering for Sequential Recommendation (2025) Sequential Recommendation with User Modeling and Profiling |