1 多行为推荐
- Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising (基于条件扩散特征去噪的多模态多行为序列推荐)
- Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
- GEAR: Generalized Alternating Regressor for Multi-Behavior Sequential Recommendation (Short Paper) (GEAR：用于多行为序列推荐的广义交替回归器)
- Junzhe Jiang, Kai Zhang, Junfeng Kang, Yucong Luo, Min Gao
2 可信推荐
- CSRec: Rethinking Sequential Recommendation from A Causal Perspective. (CSRec：从因果视角反思序列推荐)
- Xiaoyu Liu, Jiaxin Yuan, Yuhang Zhou, Jingling Li, Furong Huang, Wei Ai
- Personalized Preference Reasoning with Large Language Models for Accurate and Explainable Recommendation (基于大语言模型的个性化偏好推理用于准确和可解释推荐)
- Jieyong Kim, Hyunseo Kim, Hyunjin Cho, Seongku Kang, Buru Chang, Jinyoung Yeo, Dongha Lee
- Pre-training for Unlearning: A Model-agnostic Paradigm for Recommendation Unlearning (为遗忘学习进行预训练：一种与模型无关的推荐遗忘学习范式)
- Guoxuan Chen, Lianghao Xia, Chao Huang
- Enhancing New-item Fairness in Dynamic Recommender Systems (增强动态推荐系统中的新项目公平性)
- Huizhong Guo, Zhu Sun, Dongxia Wang, Tianjun Wei, Jinfeng Li, Jie Zhang
- FedCIA: Federated Collaborative Information Aggregation for Privacy-Preserving Recommendation (FedCIA：用于隐私保护推荐的联邦协同信息聚合)
- Mingzhe Han, Dongsheng Li, Jiafeng Xia, Jiahao Liu, Hansu Gu, Peng Zhang, Ning Gu, Tun Lu
- LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation (LLM生成的假新闻在新闻生态中引发真相衰退：基于神经新闻推荐的案例研究)
- Beizhe Hu, Qiang Sheng, Juan Cao, Yang Li, Danding Wang
- Can LLMs Enhance Fairness in Recommendation Systems? A Data Augmentation Approach (LLM能否增强推荐系统中的公平性？一种数据增强方法)
- Hanzhe Li, Dazhong Shen, Chao Wang, Yuting Liu, Jingjing Gu
- Bridging Interests and Truth: Towards Mitigating Fake News with Personalized and Truthful Recommendations (连接兴趣与真相：通过个性化和真实的推荐缓解假新闻)
- Zihan Ma, Minnan Luo, Yiran Hao, Zeng Zhi, Xiangzheng Kong, Jiahao Wang
- ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systems (无ID并非无风险：LLM驱动的智能体揭示无ID推荐系统中的风险)
- Zongwei Wang, Min Gao, Junliang Yu, Xinyi Gao, Quoc Viet Hung Nguyen, Shazia Sadiq, Hongzhi Yin
- Understanding Accuracy-Fairness Trade-offs in Re-ranking through Elasticity in Economics (通过经济学中的弹性理解重排序中的准确性-公平性权衡)
- Chen Xu, Jujia Zhao, Wang Wenjie, Liang Pang, Jun Xu, Tat-Seng Chua, Maarten de Rijke
- Fair Recommendation with Biased-Limited Sensitive Attribute (具有偏见限制敏感属性的公平推荐)
- Jizhi Zhang, Haoyu Shen, Tianhao Shi, Keqin Bao, Xin Chen, Yang Zhang, Fuli Feng
- Improving Sequential Recommenders through Counterfactual Augmentation of System Exposure (通过系统曝光的反事实增强改进序列推荐器)
- Ziqi Zhao, Zhaochun Ren, Jiyuan Yang, Zuming Yan, Zihan Wang, Liu Yang, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Xin Xin
- Social Relation-Level Privacy Risks and Preservation in Social Recommender Systems (社交推荐系统中的社交关系层面隐私风险与保护)
- Xuhao Zhao, Zhongrui Zhang, Yanmin Zhu, Zhaobo Wang, Wenze Ma, Jiadi Yu, Feilong Tang
- Balancing Self-Presentation and Self-Hiding for Exposure-Aware Recommendation Based on Graph Contrastive Learning (基于图对比学习的曝光感知推荐中的自我展示与自我隐藏平衡)
- Leqi Zheng, Chaokun Wang, Ziyang Liu, Canzhi Chen, Cheng Wu, Hongwei Li
- Disentangled Graph Debiasing for Next POI Recommendation (下一代兴趣点推荐的解耦图去偏)
- Hailun Zhou, Jiajie Xu, Qiaoming Zhu, Chengfei Liu
- Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop (探索用户、数据和推荐系统反馈回路中源偏见的升级)
- Yuqi Zhou, Sunhao Dai, Liang Pang, Gang Wang, Zhenhua Dong, Jun Xu, Ji-Rong Wen
- Refining Fidelity Metrics for Explainable Recommendations (Short Paper) (改进可解释推荐的保真度度量)
- Mikhail Baklanov, Veronika Bogina, Yehonatan Elisha, Yahlly Schein, Liron Allerhand, Oren Barkan, Noam Koenigstein
- Unbiased Collaborative Filtering with Fair Sampling (Short Paper) (基于公平采样的无偏协同过滤)
- Jiahao Liu, Dongsheng Li, Hansu Gu, Peng Zhang, Tun Lu, Li Shang, Ning Gu
- Dual Debiasing in LLM-based Recommendation (Short Paper) (LLM推荐中的双重去偏)
- Sijin Lu, Zhibo Man, Fangyuan Luo, Jun Wu
- Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M (Short Paper) (LLM会记住推荐数据集吗？MovieLens-1M的初步研究)
- Dario Di Palma, Felice Antonio Merra, Maurizio Sfilio, Vito Walter Anelli, Fedelucio Narducci, Tommaso Di Noia
- Private Preferences, Public Rankings: A Privacy-Preserving Framework for Marketplace Recommendations (Short Paper) (私有偏好，公共排名：一个用于市场推荐的隐私保护框架)
- Guilherme Ramos, Ludovico Boratto, Mirko Marras
- FairDiverse: A Comprehensive Toolkit for Fairness- and Diversity-aware Information Retrieval (Resource and Repro Paper) (FairDiverse：一个公平性和多样性感知信息检索的综合工具包)
- Chen Xu, Zhirui Deng, Clara Rus, Xiaopeng Ye, Yuanna Liu, Jun Xu, Zhicheng Dou, Ji-Rong Wen, Maarten de Rijke
- FairWork: A Generic Framework For Evaluating Fairness In LLM-Based Job Recommender System (Demonstration Paper) (FairWork：评估基于LLM的职位推荐系统公平性的通用框架)
- Yuhan Hu, Ziyu Lyu, Lu Bai, Lixin Cui
- Post-event Modeling via Causal Optimal Transport for CTR Prediction (SIRIP/Industry Track) (通过因果最优传输进行事件后建模以预测点击率)
- Yizhou Sang, Congcong Liu, Yuying Chen, Zhiwei Fang, Xue Jiang, Changping Peng, Zhangang Lin, Ching Law and Jingping Shao
- Denoising Multi-Interest-Aware Logical Reasoning for Long-Sequence Recommendation (长序列推荐中的去噪多兴趣感知逻辑推理)
- Fei Li, Qingyun Gao, Yizhou Dang, Enneng Yang, Guibing Guo, Jianzhe Zhao, Xingwei Wang
- DAR: Dimension-Adaptive Recommendation with Multi-Granular Noise Control (DAR：具有多粒度噪声控制的维度自适应推荐)
- Riwei Lai, Li Chen, Rui Chen, Chi Zhang
因果推断与反事实方法：对“如果……会怎样”这类因果问题的关注，理解和改进推荐机制
可解释性与透明度：利用大语言模型进行个性化偏好推理以提供准确且可解释的推荐，理解推荐决策
隐私保护与遗忘学习：数据隐私法规和用户隐私意识
公平性：推荐结果对不同用户和物品的公平性
bias：图解耦去偏应用于POI推荐，探索用户、数据和推荐系统反馈回路中源偏见的放大机制，以及在LLM推荐中进行双重去偏
系统鲁棒性与噪声处理：长序列推荐中的去噪多兴趣感知逻辑推理（如“Denoising Multi-Interest-Aware Logical Reasoning”），以及具有多粒度噪声控制的维度自适应推荐
3 跨域推荐
- X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation (X-Cross：面向跨域序列推荐的语言模型动态集成)
- Guy Hadad, Haggai Roitman, Yotam Eshel, Bracha Shapira, Lior Rokach
- CD-CDR: Conditional Diffusion-based Item Generation for Cross-Domain Recommendation (CD-CDR：基于条件扩散的跨域推荐物品生成)
- Hanyu Li, Jiayu Li, Weizhi Ma, Peijie Sun, Haiyang Wu, Jingwen Wang, Yang Yuekui, Min Zhang, Shaoping Ma
- Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation (连接领域：大语言模型增强的跨域序列推荐)
- Qidong Liu, Xiangyu Zhao, Yejing Wang, Zijian Zhang, Howard Zhong, Chong Chen, Xiang Li, Wei Huang, Feng Tian
- CDC: Causal Domain Clustering for Multi-Domain Recommendation (CDC：面向多域推荐的因果域聚类)
- Huishi Luo, Yiqing Wu, Yiwen Chen, Fuzhen Zhuang, Deqing Wang
- Enhancing Cross-Domain Recommendation with Plug-In Contrastive Representations from Large Language Models (利用大语言模型的可插拔对比表示增强跨域推荐)
- Ke Wang, Ji Zhang, Kuan Liu
- Adaptive Graph Integration for Cross-Domain Recommendation via Heterogeneous Graph Coordinators (通过异构图协调器实现跨域推荐的自适应图集成)
- Hengyu Zhang, Chunxu Shen, Xiangguo Sun, Jie Tan, Yu Rong, Chengzhi Piao, Hong Cheng, Lingling Yi
- AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations (Short Paper) (AgentCF++：用于流行度感知跨域推荐的记忆增强型LLM智能体)
- Jiahao Liu, Shengkang Gu, Dongsheng Li, Guangping Zhang, Mingzhe Han, Hansu Gu, Peng Zhang, Tun Lu, Li Shang, Ning Gu
- Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat (SIRIP/Industry Track) (在Snapchat利用跨域用户意图学习通用用户表征)
- Clark Mingxuan Ju, Leonardo Neves, Bhuvesh Kumar, Liam Collins, Tong Zhao, Yuwei Qiu, Ching Dou, Yang Zhou, Sohail Nizam, Rengim Aykan Ozturk, Yvette Liu, Sen Yang, Manish Malik and Neil Shah
总结：语义理解和智能体建模的大语言模型，用于数据增强或表示的扩散模型的生成能力，用于集成不同领域信息的图神经网络的结构学习能力，因果推断提供的鲁棒性，以及对学习对齐的或通用的用户表示的持续关注。许多方法也特别针对跨域的序列推荐场景中的挑战
4 序列推荐
- Unleashing the Potential of Diffusion Models Towards Diversified Sequential Recommendations (释放扩散模型在多样化序列推荐中的潜力)
- Zhuo Cai, Shoujin Wang, Victor W. Chu, Usman Naseem, Yang Wang, Fang Chen
- Dynamic Time-aware Continual User Representation Learning (动态时间感知的持续用户表征学习)
- Seungyoon Choi, Sein Kim, Hong-Seok Kang, Wonjoong Kim, Chanyoung Park
- Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising (基于条件扩散特征去噪的多模态多行为序列推荐)
- Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
- Data Augmentation as Free Lunch: Exploring the Test-Time Augmentation for Sequential Recommendation (数据增强的免费午餐：探索序列推荐的测试时增强)
- Yizhou Dang, Yuting Liu, Enneng Yang, Minhan Huang, Guibing Guo, Jianzhe Zhao, Xingwei Wang
- X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation (X-Cross：面向跨域序列推荐的语言模型动态集成)
- Guy Hadad, Haggai Roitman, Yotam Eshel, Bracha Shapira, Lior Rokach
- Short Video Segment-level User Dynamic Interests Modeling in Personalized Recommendation (短视频片段级用户动态兴趣建模在个性化推荐中的应用)
- Zhiyu He, Zhixin Ling, Jiayu Li, Zhiqiang Guo, Weizhi Ma, Xinchen Luo, Min Zhang, Guorui Zhou
- AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings (AlphaFuse：在语言嵌入零空间中学习序列推荐的ID嵌入)
- Guoqing Hu, An Zhang, Shuo Liu, Zhibo Cai, Xun Yang, Xiang Wang
- DIFF: Dual Side-Information Filtering and Fusion for Sequential Recommendation (DIFF：用于序列推荐的双边信息过滤与融合)
- Hye-young Kim, Minjin Choi, Sunkyung Lee, Ilwoong Baek, Jongwuk Lee
- Denoising Multi-Interest-Aware Logical Reasoning for Long-Sequence Recommendation (长序列推荐中的去噪多兴趣感知逻辑推理)
- Fei Li, Qingyun Gao, Yizhou Dang, Enneng Yang, Guibing Guo, Jianzhe Zhao, Xingwei Wang
- Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation (连接领域：大语言模型增强的跨域序列推荐)
- Qidong Liu, Xiangyu Zhao, Yejing Wang, Zijian Zhang, Howard Zhong, Chong Chen, Xiang Li, Wei Huang, Feng Tian
- Mitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective (缓解序列推荐中的分布偏移：不变性视角)
- Yuxin Liao, Yonghui Yang, Min Hou, Le Wu, Hefei Xu, Hao Liu
- Towards Interest Drift-driven User Representation Learning in Sequential Recommendation (面向兴趣漂移驱动的序列推荐用户表征学习)
- Xiaolin Lin, Weike Pan, Zhong Ming
- CSRec: Rethinking Sequential Recommendation from A Causal Perspective. (CSRec：从因果视角反思序列推荐)
- Xiaoyu Liu, Jiaxin Yuan, Yuhang Zhou, Jingling Li, Furong Huang, Wei Ai
- Intent-aware Diffusion with Contrastive Learning for Sequential Recommendation (基于对比学习的意图感知扩散序列推荐)
- Yuanpeng Qu, Hajime Nobuhara
- Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models (预训练、对齐与解耦：用大语言模型赋能序列推荐)
- Yuhao Wang, Junwei Pan, Pengyue Jia, Wanyu Wang, Maolin Wang, Zhixiang Feng, Xiaotian Li, Jie Jiang, Xiangyu Zhao
- STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation (STAR-Rec：应对序列推荐中的长度差异和模式多样性)
- Maolin Wang, Sheng Zhang, Ruocheng Guo, Wanyu Wang, Xuetao Wei, Zitao Liu, Hongzhi Yin, Yi Chang, Xiangyu Zhao
- Triplet Contrastive Learning with Learnable Sequence Augmentation for Sequential Recommendation (基于可学习序列增强的三元组对比学习序列推荐)
- Wei Wang, Yujie Lin, Moyan Zhang, Lu Hongyu, Jianli Zhao, Jie Sun, Xianye Ben, Pengjie Ren, Yujun Li
- Embracing Plasticity: Balancing Stability and Plasticity in Continual Recommender Systems (拥抱可塑性：在持续推荐系统中平衡稳定性与可塑性)
- Hyunsik Yoo, Seongku Kang, Ruizhong Qiu, Charlie Xu, Fei Wang, Hanghang Tong
- CoMaPOI: A Collaborative Multi-Agent Framework for Next POI Prediction Bridging the Gap Between Trajectory and Language (CoMaPOI：连接轨迹与语言的协作式多智能体下一代兴趣点预测框架)
- Lin Zhong, Lingzhi Wang, Xu Yang, Qing Liao
- Diversity-aware Dual-promotion Poisoning Attack on Sequential Recommendation (序列推荐中的多样性感知双重提升投毒攻击)
- Yuchuan Zhao, Tong Chen, Junliang Yu, Kai Zheng, Lizhen Cui, Hongzhi Yin
- Improving Sequential Recommenders through Counterfactual Augmentation of System Exposure (通过系统曝光的反事实增强改进序列推荐器)
- Ziqi Zhao, Zhaochun Ren, Jiyuan Yang, Zuming Yan, Zihan Wang, Liu Yang, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Xin Xin
- Disentangled Graph Debiasing for Next POI Recommendation (下一代兴趣点推荐的解耦图去偏)
- Hailun Zhou, Jiajie Xu, Qiaoming Zhu, Chengfei Liu
- Adaptive user Dynamic Interest Guidance for Generative Sequential Recommendation (生成式序列推荐的自适应用户动态兴趣引导)
- Kai Zhu, Jing Li, Jia Wu, Yue He, Jun Chang, Guohao Li, Shuyi Zhang
- Interest Changes: Considering User Interest Life Cycle in Recommendation System (Short Paper) (兴趣变迁：推荐系统中用户兴趣生命周期的考量)
- Yinjiang Cai, Jiangpan Hou, Yangping Zhu, Nie Yuan
- HeterRec: Heterogeneous Information Transformer for Scalable Sequential Recommendation (Short Paper) (HeterRec：用于可扩展序列推荐的异构信息Transformer)
- Hao Deng, Haibo Xing, Kanefumi Matsuyama, Yulei Huang, Jinxin Hu, Hong Wen, Jia Xu, Zulong Chen, Yu Zhang, Xiaoyi Zeng, Jing Zhang
- Training-free Periodic Interest Augmentation in Incremental Recommendation (Short Paper) (增量推荐中无需训练的周期性兴趣增强)
- Heyuan Huang, Xingyu Lou, Changwang Zhang, Chaochao Chen, Kuiyao Dong, Feng Lu, Han Lei, Yihao Wang, Wangchunshu Zhou, Jun Wang
- GEAR: Generalized Alternating Regressor for Multi-Behavior Sequential Recommendation (Short Paper) (GEAR：用于多行为序列推荐的广义交替回归器)
- Junzhe Jiang, Kai Zhang, Junfeng Kang, Yucong Luo, Min Gao
- SEALR: Sequential Emotion-Aware LLM-Based Personalized Recommendation System (Short Paper) (SEALR：基于序列情感感知LLM的个性化推荐系统)
- Namjun Lee, Jaekwang Kim
- Reassessing the Effectiveness of Reinforcement Learning based Recommender Systems for Sequential Recommendation (Resource and Repro Paper) (重新评估基于强化学习的序列推荐系统有效性)
- Dilina Chandika Rajapakse, Dietmar Jannach
- Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders (SIRIP/Industry Track) (推荐系统中个性化序列建模的自适应领域缩放)
- Zheng Chai, Hui Lu, Di Chen, Qin Ren, Yuchao Zheng and Xun Zhou
- Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation (SIRIP/Industry Track) (金字塔混合器：序列推荐的多维多周期兴趣建模)
- Zhen Gong, Zhifang Fang, Hui Lu, Qiwei Chen, Chenbin Zhang, Lin Guan, Yuchao Zheng, Feng Zhang, Xiao Yang and Zuotao Liu
深度融合与创新应用先进的生成式模型（如扩散模型实现多样性生成与特征去噪，大语言模型赋能零空间ID嵌入、情感感知及生成式兴趣引导），同时在精细化用户动态性与持续学习建模（例如引入可塑性平衡、免训练增量学习、兴趣生命周期考量及长序列逻辑推理）、开拓鲁棒性与因果认知新范式（通过新颖数据增强、不变性视角抗分布偏移、以及从因果与反事实角度重构推荐逻辑）方面取得了重要进展。此外，研究者们还积极探索了针对序列特性的新颖网络架构、多智能体协作、复杂场景下的多模态多行为融合以及前瞻性的安全防护等方向，共同推动序列推荐向更智能、鲁棒和可信的未来演进。
5 基于图的推荐
- oRec: Enhancing Recommendation with Voronoi Diagram in Hyperbolic Space (VoRec：在双曲空间中利用Voronoi图增强推荐)
- Yong Chen, Li Li, Wei Peng, Songzhi Su
- CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Models (CORONA：一种基于大语言模型的图推荐由粗到精框架)
- Junze Chen, Xinjie Yang, Cheng Yang, Junfei Bao, Zeyuan Guo, Yawen Li, Chuan Shi
- Large Language Models Enhanced Hyperbolic Space Recommender Systems (大语言模型增强的双曲空间推荐系统)
- Wentao Cheng, Zhida Qin, Zexue Wu, Pengzhan Zhou, Tianyu Huang
- Comprehending Knowledge Graphs with Large Language Models for Recommender Systems (面向推荐系统的大语言模型知识图谱理解)
- Ziqiang Cui, Yunpeng Weng, Xing Tang, Fuyuan Lyu, Dugang Liu, Xiuqiang He, Chen Ma
- Graph Spectral Filtering with Chebyshev Interpolation for Recommendation (基于切比雪夫插值的图谱滤波推荐)
- Chanwoo Kim, Jinkyu Sung, Yebonn Han, Joonseok Lee
- Hypercomplex Knowledge Graph-Aware Recommendation (超复数知识图谱感知推荐)
- Anchen Li, Bo Yang, Huan Huo, Farookh Hussain, Guandong Xu
- Rating-Aware Homogeneous Review Graphs and User Likes/Dislikes Differentiation for Effective Recommendations (有效推荐中的评分感知同构评论图与用户喜好区分)
- Jiwon Son, Hyunjoon Kim, Sang-Wook Kim
- MSCRS: Multi-modal Semantic Graph Prompt Learning Framework for Conversational Recommender Systems (MSCRS：面向对话式推荐系统的多模态语义图提示学习框架)
- Yibiao Wei, Jie Zou, Weikang Guo, Guoqing Wang, Xing Xu, Yang Yang
- COHESION: Composite Graph Convolutional Network with Dual-Stage Fusion for Multimodal Recommendation (COHESION：用于多模态推荐的双阶段融合复合图卷积网络)
- Jinfeng Xu, Zheyu Chen, Wei Wang, Xiping Hu, Sang-Wook Kim, Edith Ngai
- Invariance Matters: Empowering Social Recommendation via Graph Invariant Learning (不变性至关重要：通过图不变学习赋能社交推荐)
- Yonghui Yang, Le Wu, Yuxin Liao, Zhuangzhuang He, Pengyang Shao, Richang Hong, Meng Wang
- Adaptive Graph Integration for Cross-Domain Recommendation via Heterogeneous Graph Coordinators (通过异构图协调器实现跨域推荐的自适应图集成)
- Hengyu Zhang, Chunxu Shen, Xiangguo Sun, Jie Tan, Yu Rong, Chengzhi Piao, Hong Cheng, Lingling Yi
- Balancing Self-Presentation and Self-Hiding for Exposure-Aware Recommendation Based on Graph Contrastive Learning (基于图对比学习的曝光感知推荐中的自我展示与自我隐藏平衡)
- Leqi Zheng, Chaokun Wang, Ziyang Liu, Canzhi Chen, Cheng Wu, Hongwei Li
- Disentangled Graph Debiasing for Next POI Recommendation (下一代兴趣点推荐的解耦图去偏)
- Hailun Zhou, Jiajie Xu, Qiaoming Zhu, Chengfei Liu
- Squeeze and Excitation: A Weighted Graph Contrastive Learning for Collaborative Filtering (Short Paper) (挤压与激励：一种用于协同过滤的加权图对比学习)
- Zheyu Chen, Jinfeng Xu, Yutong Wei, Ziyue Peng
- Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph (Resource and Repro Paper) (基于Hugging Face知识图谱的推荐、分类和追踪基准测试)
- Qiaosheng Chen, Kaijia Huang, Xiao Zhou, Weiqing Luo, Yuanning Cui, Gong Cheng
图神经网络（GNNs）与大语言模型（LLM）的深度协同（例如LLM被用于增强双曲空间图推荐、辅助知识图谱的理解、以及实现图上的提示学习，常结合由粗到精的框架），以及对高级图结构、新颖几何空间（如双曲空间与Voronoi图的结合应用、引入超复数进行知识图谱表示）与创新学习范式（如图谱滤波新方法、旨在提升社交推荐鲁棒性的图不变学习、以及应用于曝光感知和协同过滤等场景的多样化图对比学习）的深入探索。同时，研究者们也积极利用图的强大表征与整合能力，针对复杂的推荐场景（如通过异构图协调器实现跨域自适应集成、利用解耦图学习进行去偏、以及作为多模态信息融合的核心框架）提出了有效的图解决方案，并通过更精细化的图构建方法（例如从评论中构建评分感知的同构图并区分用户喜好）与特征区分来进一步提升推荐性能，共同推动图推荐技术向更深层次的理解、更强的表征能力及更广泛的应用领域迈进。
6 多模态推荐
- Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising (基于条件扩散特征去噪的多模态多行为序列推荐)
- Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
- Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction (基于扩散的多模态协同兴趣网络用于点击率预估)
- Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
- MELON: Learning Multi-Aspect Modality Preferences for Accurate Multimedia Recommendation (MELON：学习多方面模态偏好以实现精准多媒体推荐)
- Dongho Jeong, Taeri Kim, Donghyeon Cho, Sang-Wook Kim
- Disentangling and Generating Modalities for Recommendation in Missing Modality Scenarios (缺失模态场景下推荐的模态解耦与生成)
- Jiwan Kim, Hong-Seok Kang, Sein Kim, Kibum Kim, Chanyoung Park
- Generating Difficulty-aware Negative Samples via Conditional Diffusion for Multi-modal Recommendation (通过条件扩散为多模态推荐生成难度感知的负样本)
- Wenze Ma, Chenyu Sun, Yanmin Zhu, Zhaobo Wang, Xuhao Zhao, Mengyuan Jing, Jiadi Yu, Feilong Tang
- MSCRS: Multi-modal Semantic Graph Prompt Learning Framework for Conversational Recommender Systems (MSCRS：面向对话式推荐系统的多模态语义图提示学习框架)
- Yibiao Wei, Jie Zou, Weikang Guo, Guoqing Wang, Xing Xu, Yang Yang
- COHESION: Composite Graph Convolutional Network with Dual-Stage Fusion for Multimodal Recommendation (COHESION：用于多模态推荐的双阶段融合复合图卷积网络)
- Jinfeng Xu, Zheyu Chen, Wei Wang, Xiping Hu, Sang-Wook Kim, Edith Ngai
突出了生成式扩散模型的多样化创新应用，例如在多模态多行为序列推荐中进行特征去噪、构建协同兴趣网络以优化点击率预估、以及生成难度感知的负样本来提升模型训练效果。同时，研究热点也集中在更精细化的模态表征学习与高效融合机制上，例如学习用户在不同模态下的多方面偏好（如MELON），以及设计新颖的复合图卷积网络结构并结合双阶段融合策略（如COHESION）以增强模态间的协同。此外，通过模态解耦与生成技术来应对现实场景中模态数据缺失的挑战，并将多模态理解与图结构、图上提示学习、对话式推荐系统及复杂行为序列建模等先进范式深度结合（如MSCRS），共同推动多模态推荐系统向更精准、鲁棒和场景适应性更强的方向发展。
7 协同过滤
- Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation (结合协同过滤的检索增强生成用于个性化文本生成)
- Teng Shi, Jun Xu, Xiao Zhang, Xiaoxue Zang, Kai Zheng, Yang Song, Han Li
- Unveiling Contrastive Learning's Capability of Neighborhood Aggregation for Collaborative Filtering (揭示对比学习在协同过滤中邻域聚合的能力)
- Yu Zhang, Yiwen Zhang, Yi Zhang, Lei Sang, Yun Yang
- Towards Distribution Matching between Collaborative and Language Spaces for Generative Recommendation (生成式推荐中协同空间与语言空间的分布匹配研究)
- Yi Zhang, Yiwen Zhang, Yu Wang, Tong Chen, Hongzhi Yin
- Squeeze and Excitation: A Weighted Graph Contrastive Learning for Collaborative Filtering (Short Paper) (挤压与激励：一种用于协同过滤的加权图对比学习)
- Zheyu Chen, Jinfeng Xu, Yutong Wei, Ziyue Peng
- Unbiased Collaborative Filtering with Fair Sampling (Short Paper) (基于公平采样的无偏协同过滤)
- Jiahao Liu, Dongsheng Li, Hansu Gu, Peng Zhang, Tun Lu, Li Shang, Ning Gu
将协同过滤的原理与检索增强生成（RAG）等大语言模型技术结合，拓展其应用至个性化文本生成等新领域，并探索如何将传统的协同信号与语言模型的丰富语义空间进行有效对齐与分布匹配，以赋能更强的生成式推荐能力 。其次，研究者们进一步深化了对对比学习在增强协同过滤效果（尤其是在理解其邻域聚合能力方面）及其在加权图方法（例如引入Squeeze-and-Excitation等机制）中应用的探索与理解 。最后，通过公平采样等具体技术手段对协同过滤方法进行去偏优化，以期获得更公正、无偏见的推荐结果，也是一个显著的研究焦点 。
8 强化学习
- Techie: Tackling Video Prefetching at Edge Networks as POMDP Via an Intrinsically Motivated RL Agent (Techie：通过内在激励强化学习智能体将边缘网络视频预取问题建模为POMDP)
- Nawras Alkassab, Chin-Tser Huang, Tania Lorido Botran
- DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward (DARLR：具有动态奖励的推荐系统双智能体离线强化学习)
- Yi Zhang, Ruihong Qiu, Xuwei Xu, Jiajun Liu, Sen Wang
- Reassessing the Effectiveness of Reinforcement Learning based Recommender Systems for Sequential Recommendation (Resource and Repro Paper) (重新评估基于强化学习的序列推荐系统有效性)
- Dilina Chandika Rajapakse, Dietmar Jannach
在新兴问题领域应用（如利用部分可观察马尔可夫决策过程模型和内在激励智能体解决边缘网络视频预取问题）的创新探索 。同时，研究趋势显著倾向于更实用和更高级的RL方法论，特别是包含了动态奖励机制的双智能体离线强化学习框架，以更好地适应真实推荐系统的复杂需求和实际部署条件 。此外，该领域也开始强调对现有基于RL的推荐方法（尤其是在序列推荐中）进行严格的有效性再评估与审视 。
9 扩散模型
- Unleashing the Potential of Diffusion Models Towards Diversified Sequential Recommendations (释放扩散模型在多样化序列推荐中的潜力)
- Zhuo Cai, Shoujin Wang, Victor W. Chu, Usman Naseem, Yang Wang, Fang Chen
- Collaborative Signal-guided Diffusion Models for Recommendation (协同信号引导的推荐扩散模型)
- Mengru Chen, Lianghao Xia, Yong Xu, Ronghua Luo
- Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising (基于条件扩散特征去噪的多模态多行为序列推荐)
- Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
- Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction (基于扩散的多模态协同兴趣网络用于点击率预估)
- Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
- CD-CDR: Conditional Diffusion-based Item Generation for Cross-Domain Recommendation (CD-CDR：基于条件扩散的跨域推荐物品生成)
- Hanyu Li, Jiayu Li, Weizhi Ma, Peijie Sun, Haiyang Wu, Jingwen Wang, Yang Yuekui, Min Zhang, Shaoping Ma
- Generating Difficulty-aware Negative Samples via Conditional Diffusion for Multi-modal Recommendation (通过条件扩散为多模态推荐生成难度感知的负样本)
- Wenze Ma, Chenyu Sun, Yanmin Zhu, Zhaobo Wang, Xuhao Zhao, Mengyuan Jing, Jiadi Yu, Feilong Tang
- Addressing Missing Data Issue for Diffusion-based Recommendation (解决基于扩散的推荐中的缺失数据问题)
- Wenyu Mao, Zhengyi Yang, Jiancan Wu, Haozhe Liu, Yancheng Yuan, Xiang Wang, Xiangnan He
- Intent-aware Diffusion with Contrastive Learning for Sequential Recommendation (基于对比学习的意图感知扩散序列推荐)
- Yuanpeng Qu, Hajime Nobuhara
利用扩散模型来提升序列推荐的多样性，在复杂的多模态多行为场景下进行条件化特征去噪，以及为点击率预估构建协同化的多模态兴趣网络。不仅如此，研究者们还致力于运用扩散模型进行跨域推荐中的条件性物品生成，为多模态推荐生成难度感知的负样本，以及解决推荐场景中的数据缺失问题。在方法层面，一个显著的趋势是通过协同信号和精细的条件控制来引导扩散过程，并将其与对比学习等其他学习范式结合以实现意图感知
10 推荐系统评测、数据集与工具
- LM-Empowered Creator Simulation for Long-Term Evaluation of Recommender Systems Under Information Asymmetry (信息不对称下LLM赋能的创作者模拟用于推荐系统长期评估)
- Xiaopeng Ye, Chen Xu, Zhongxiang Sun, Jun Xu, Gang Wang, Zhenhua Dong, Ji-Rong Wen
- PUB: An LLM-Enhanced Personality-Driven User Behaviour Simulator for Recommender System Evaluation (Short Paper) (PUB：一个用于推荐系统评估的LLM增强人格驱动用户行为模拟器)
- Chenglong Ma, Ziqi Xu, Yongli Ren, Danula Hettiachchi, Jeffrey Chan
- LLM as User Simulator: Towards Training News Recommender without Real User Interactions (Short Paper) (LLM作为用户模拟器：迈向无需真实用户交互的新闻推荐器训练)
- Choongwon Park
- From Monolith to Mosaic: Uncovering Behavioral Differences for Choice Models in Recommender Systems Simulations (Short Paper) (从单体到马赛克：揭示推荐系统模拟中选择模型的行为差异)
- Robin Ungruh, Alejandro Bellogin, Maria Soledad Pera
- CoSRec: A Joint Conversational Search and Recommendation Dataset (Resource and Repro Paper) (CoSRec：一个联合对话式搜索与推荐数据集)
- Marco Alessio, Simone Merlo, Tommaso Di Noia, Guglielmo Faggioli, Marco Ferrante, Nicola Ferro, Cristina Ioana Muntean, Franco Maria Nardini, Fedelucio Narducci, Raffaele Perego, Giuseppe Santucci, Nicola Viterbo
- SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Data Generation for Personalized Tourism Recommenders (Resource and Repro Paper) (SynthTRIPs：一个用于个性化旅游推荐器基准数据生成的知识驱动框架)
- Ashmi Banerjee, Adithi Satish, Fitri Nur Aisyah, Wolfgang Wörndl, Yashar Deldjoo
- U-Sticker: A Large-Scale Multi-Domain User Sticker Dataset for Retrieval and Personalization (Resource and Repro Paper) (U-Sticker：一个用于检索和个性化的大规模多领域用户贴纸数据集)
- Heng Er Metilda Chee, Jiayin Wang, Zhiqiang Guo, Weizhi Ma, Qinglang Guo, Min Zhang
- Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph (Resource and Repro Paper) (基于Hugging Face知识图谱的推荐、分类和追踪基准测试)
- Qiaosheng Chen, Kaijia Huang, Xiao Zhou, Weiqing Luo, Yuanning Cui, Gong Cheng
- RecGaze: The First Eye Tracking and User Interaction Dataset for Carousel Interfaces (Resource and Repro Paper) (RecGaze：第一个用于轮播界面的眼动追踪和用户交互数据集)
- Santiago de Leon-Martinez, Jingwei Kang, Robert Moro, Maarten de Rijke, Branislav Kveton, Harrie Oosterhuis, Maria Bielikova
- DataRec: A Python Library for Standardized and Reproducible Data Management in Recommender Systems (Resource and Repro Paper) (DataRec：一个用于推荐系统中标准化和可复现数据管理的Python库)
- Alberto Carlo Maria Mancino, Salvatore Bufi, Angela Di Fazio, Antonio Ferrara, Daniele Malitesta, Claudio Pomo, Tommaso Di Noia
- Reassessing the Effectiveness of Reinforcement Learning based Recommender Systems for Sequential Recommendation (Resource and Repro Paper) (重新评估基于强化学习的序列推荐系统有效性)
- Dilina Chandika Rajapakse, Dietmar Jannach
- A Worrying Reproducibility Study of Intent-Aware Recommendation Models (Resource and Repro Paper) (一项关于意图感知推荐模型可复现性的令人担忧的研究)
- Faisal Shehzad, Maurizio Ferrari Dacrema, Dietmar Jannach
- Extending MovieLens-32M to Provide New Evaluation Objectives (Resource and Repro Paper) (扩展MovieLens-32M以提供新的评估目标)
- Mark Smucker, Houmaan Chamani
- FairDiverse: A Comprehensive Toolkit for Fairness- and Diversity-aware Information Retrieval (Resource and Repro Paper) (FairDiverse：一个公平性和多样性感知信息检索的综合工具包)
- Chen Xu, Zhirui Deng, Clara Rus, Xiaopeng Ye, Yuanna Liu, Jun Xu, Zhicheng Dou, Ji-Rong Wen, Maarten de Rijke
- NodeRec+: A Lightweight Framework for Federated Recommender Systems (Demonstration Paper) (NodeRec+：一个轻量级的联邦推荐系统框架)
- Diarmuid Morgan, Erika Duriakova, Elias Tragos, Neil Hurley, Aonghus Lawlor
- Toward Holistic Evaluation of Recommender Systems Powered by Generative Models (Perspectives) (迈向生成模型驱动推荐系统的整体评估)
- Yashar Deldjoo, Nikhil Mehta, Maheswaran Sathiamoorthy, Shuai Zhang, Pablo Castells, Julian McAuley
11 通用技术
- MGIPF: Multi-Granularity Interest Prediction Framework for Personalized Recommendation (MGIPF：个性化推荐的多粒度兴趣预测框架)
- Ruoxuan Feng, Zhen Tian, Qiushi Peng, Jiaxin Mao, Xin Zhao, Di Hu, Changwang Zhang
- DAR: Dimension-Adaptive Recommendation with Multi-Granular Noise Control (DAR：具有多粒度噪声控制的维度自适应推荐)
- Riwei Lai, Li Chen, Rui Chen, Chi Zhang
- Bridging Interests and Truth: Towards Mitigating Fake News with Personalized and Truthful Recommendations (连接兴趣与真相：通过个性化和真实的推荐缓解假新闻)
- Zihan Ma, Minnan Luo, Yiran Hao, Zeng Zhi, Xiangzheng Kong, Jiahao Wang
- Why is Normalization Necessary for Linear Recommenders? (为什么归一化对线性推荐器是必要的？)
- Seongmin Park, Mincheol Yoon, Hye-young Kim, Jongwuk Lee
- Multi-scenario Instance Embedding Learning for Deep Recommender Systems (深度推荐系统的多场景实例嵌入学习)
- Chaohua Yang, Dugang Liu, Xing Tang, Yuwen Fu, Xiuqiang He, Xiangyu Zhao, Zhong Ming
- SEALR: Sequential Emotion-Aware LLM-Based Personalized Recommendation System (Short Paper) (SEALR：基于序列情感感知LLM的个性化推荐系统)
- Namjun Lee, Jaekwang Kim
- Multi-Interest Matching for Personalized News Recommendation with Large Language Models (Short Paper) (基于大语言模型的多兴趣匹配个性化新闻推荐)
- Hongxiang Lin, Yixiao Zhou, Huiying Hu, Xiaoqing Lyu
- Improving LLM-powered Recommendations with Personalized Information (Short Paper) (利用个性化信息改进LLM驱动的推荐)
- Jiahao Liu, Xueshuo Yan, Dongsheng Li, Guangping Zhang, Hansu Gu, Peng Zhang, Tun Lu, Li Shang, Ning Gu
- NAM: A Normalization Attention Model for Personalized Product Search In Fliggy (Short Paper) (NAM：飞猪个性化商品搜索的归一化注意力模型)
- Shui Liu, Mingyuan Tao, Maofei Que, Pan Li, Dong Li, Shenghua Ni, Zhuoran Zhuang
- SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Data Generation for Personalized Tourism Recommenders (Resource and Repro Paper) (SynthTRIPs：一个用于个性化旅游推荐器基准数据生成的知识驱动框架)
- Ashmi Banerjee, Adithi Satish, Fitri Nur Aisyah, Wolfgang Wörndl, Yashar Deldjoo
- U-Sticker: A Large-Scale Multi-Domain User Sticker Dataset for Retrieval and Personalization (Resource and Repro Paper) (U-Sticker：一个用于检索和个性化的大规模多领域用户贴纸数据集)
- Heng Er Metilda Chee, Jiayin Wang, Zhiqiang Guo, Weizhi Ma, Qinglang Guo, Min Zhang
- Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders (SIRIP/Industry Track) (推荐系统中个性化序列建模的自适应领域缩放)
- Zheng Chai, Hui Lu, Di Chen, Qin Ren, Yuchao Zheng and Xun Zhou
- IRA: Adaptive Interest-aware Representation and Alignment for Personalized Multi-interest Retrieval (SIRIP/Industry Track) (IRA：个性化多兴趣检索的自适应兴趣感知表征与对齐)
- Youngjune Lee, Haeyu Jeong, Changgeon Lim, Jeong Choi, Hongjun Lim, Hangon Kim, Jiyoon Kwon and Saehun Kim
- PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval (SIRIP/Industry Track) (PaRT：通过个性化实时检索增强主动式社交聊天机器人)
- Zihan Niu, Zheyong Xie, Shaosheng Cao, Chonggang Lu, Zheyu Ye, Tong Xu, Zuozhu Liu, Yan Gao, Jia Chen, Zhe Xu, Yi Wu and Yao Hu
11 CTR和推荐排序
- Unconstrained Monotonic Calibration of Predictions in Deep Ranking Systems (深度排序系统中预测的无约束单调校准)
- Yimeng Bai, Shunyu Zhang, Yang Zhang, Hu Liu, Wentian Bao, Enyun Yu, Fuli Feng, Wenwu Ou
- Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction (基于扩散的多模态协同兴趣网络用于点击率预估)
- Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
- Generative Auto-Bidding with Value-Guided Explorations (价值引导探索的生成式自动出价)
- Jingtong Gao, Yewen Li, Shuai Mao, Peng Jiang, Nan Jiang, Yejing Wang, Qingpeng Cai, Fei Pan, Peng Jiang, Kun Gai, Bo An, Xiangyu Zhao
- DLF: Enhancing Explicit-Implicit Interaction via Dynamic Low-Order-Aware Fusion for CTR Prediction (DLF：通过动态低阶感知融合增强显式-隐式交互以进行CTR预测)
- Kefan Wang, Hao Wang, Wei Guo, Yong Liu, Jianghao Lin, Defu Lian, Enhong Chen
- A Learnable Fully Interacted Two-Tower Model for Pre-Ranking System (可学习的全交互双塔模型用于预排序系统)
- Chao Xiong, Xianwen Yu, Wei Xu, Lei Cheng, Chuan Yuan, Linjian Mo
- Understanding Accuracy-Fairness Trade-offs in Re-ranking through Elasticity in Economics (通过经济学中的弹性理解重排序中的准确性-公平性权衡)
- Chen Xu, Jujia Zhao, Wang Wenjie, Liang Pang, Jun Xu, Tat-Seng Chua, Maarten de Rijke
- Adaptive Structure Learning with Partial Parameter Sharing for Post-Click Conversion Rate Prediction (用于点击后转化率预测的部分参数共享自适应结构学习)
- Chunyuan Zheng, Hang Pan, Yang Zhang, Haoxuan Li
- ELEC: Efficient Large Language Model-empowered Click-Through Rate Prediction (Short Paper) (ELEC：高效大语言模型赋能的点击率预估)
- Rui Dong, Wentao Ouyang, Xiangzheng Liu
- Towards Principled Learning for Re-ranking in Recommender Systems (Short Paper) (迈向推荐系统中重排序的原则性学习)
- Qunwei Li, Linghui Li, Jianbin Lin, Wenliang Zhong
- SMMR: Sampling-Based MMR Reranking for Faster, More Diverse, and Balanced Recommendations and Retrieval (Short Paper) (SMMR：基于采样的MMR重排序，实现更快、更多样化、更平衡的推荐和检索)
- Kiryl Liakhnovich, Oleg Lashinin, Andrei Babkin, Michael Pechatov, Marina Ananyeva
- Hierarchical User Long-term Behavior Modeling for Click-Through Rate Prediction (Short Paper) (点击率预测的层次化用户长期行为建模)
- Mao Pan, Xuanhua Yang, Nan Qiao, Dongyue Wang, Feng Mei, Xiwei Zhao, Sulong Xu
- LREA: Low-Rank Efficient Attention on Modeling Long-Term User Behaviors for CTR Prediction (Short Paper) (LREA：用于CTR预测的长期用户行为建模的低秩高效注意力机制)
- Xin Song, Xiaochen Li, Jinxin Hu, Hong Wen, Zulong Chen, Yu Zhang, Xiaoyi Zeng, Jing Zhang
- Deep Multiple Quantization Network on Long Behavior Sequence for Click-Through Rate Prediction (Short Paper) (长行为序列上的深度多重量化网络用于点击率预测)
- Zhuoxing Wei, Qi Liu, Qingchen Xie
- GRAIN: Group-Reinforced Adaptive Interaction Network for Cold-Start CTR Prediction in E-commerce Search (SIRIP/Industry Track) (GRAIN：电商搜索中冷启动CTR预测的组增强自适应交互网络)
- Wei Bao, Hao Chen, Bang Lin, Tao Zhang and Chengfu Huo
- A Generative Re-ranking Model for List-level Multi-objective Optimization at Taobao (SIRIP/Industry Track) (淘宝列表级多目标优化的生成式重排模型)
- Yue Meng, Cheng Guo, Yi Cao, Tong Liu and Bo Zheng
- Post-event Modeling via Causal Optimal Transport for CTR Prediction (SIRIP/Industry Track) (通过因果最优传输进行事件后建模以预测点击率)
- Yizhou Sang, Congcong Liu, Yuying Chen, Zhiwei Fang, Xue Jiang, Changping Peng, Zhangang Lin, Ching Law and Jingping Shao
- SuperRS: Multi Scenario Reciprocal-Aware Dual MoE for Unified Recommendation-Search Ranking (SIRIP/Industry Track) (SuperRS：用于统一推荐搜索排序的多场景互惠感知双MoE模型)
- Zihan Xia, Chuanyu Xu, Tao Zhang and Chengfu Huo