ACM SIGKDD(国际数据挖掘与知识发现大会,简称KDD)会议始于1989年,是数据挖掘领域历史最悠久、规模最大的国际顶级学术会议,也是首个引入大数据、数据科学、预测分析、众包等概念的会议,每年吸引了大量数据挖掘、机器学习、大数据和人工智能等领域的研究学者、从业人员参与。
AMiner通过AI技术,对 KDD2023 收录的会议论文进行了分类整理,今日分享的是Recommendation主题论文!(由于篇幅关系,本篇只展现部分论文,点击阅读原文可直达KDD顶会页面查看所有论文)
1.Adaptive Graph Contrastive Learning for Recommendation
链接:https://www.aminer.cn/pub/6466fafbd68f896efaeb7633/
2.Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation
链接:https://www.aminer.cn/pub/648000a9d68f896efaa123eb/
3.Multi-channel Integrated Recommendation with Exposure Constraints
链接:https://www.aminer.cn/pub/646c3ad0d68f896efa5ce60f/
4.ReLoop2: Building Self-Adaptive Recommendation Models via Responsive Error Compensation Loop
链接:https://www.aminer.cn/pub/648bde68d68f896efaf81bd3/
5.Hierarchical Invariant Learning for Domain Generalization Recommendation
链接:https://www.aminer.cn/pub/64af9a073fda6d7f065a6d92/
6.Debiasing Recommendation by Learning Identifiable Latent Confounders
链接:https://www.aminer.cn/pub/63e9aa5e90e50fcafd133661/
7.Meta Graph Learning for Long-tail Recommendation
链接:https://www.aminer.cn/pub/64af9a033fda6d7f065a6963/
8.PGLBox: Multi-GPU Graph Learning Framework for Web-Scale Recommendation
链接:https://www.aminer.cn/pub/64af9a043fda6d7f065a6a90/
9.Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay
链接:https://www.aminer.cn/pub/64af9a063fda6d7f065a6b9c/
10.Privacy Matters: Vertical Federated Linear Contextual Bandits for Privacy Protected Recommendation
链接:https://www.aminer.cn/pub/64af9a0a3fda6d7f065a702d/
11.Generative Flow Network for Listwise Recommendation
链接:https://www.aminer.cn/pub/64af99fc3fda6d7f065a6275/
12.A Sublinear Time Algorithm for Opinion Optimization in Directed Social Networks via Edge Recommendation
链接:https://www.aminer.cn/pub/64af99fc3fda6d7f065a62a4/
13.Hierarchical Projection Enhanced Multi-behavior Recommendation
链接:https://www.aminer.cn/pub/64af99fe3fda6d7f065a6424/
14.SAMD: An Industrial Framework for Heterogeneous Multi-Scenario Recommendation
链接:https://www.aminer.cn/pub/64af99fe3fda6d7f065a6481/
15.M5: Multi-Modal Multi-Interest Multi-Scenario Matching for Over-the-Top Recommendation
链接:https://www.aminer.cn/pub/64af9a033fda6d7f065a691f/
16.Modeling Dual Period-Varying Preferences for Takeaway Recommendation
链接:https://www.aminer.cn/pub/64af9a053fda6d7f065a6b8b/
17.Reconsidering Learning Objectives in Unbiased Recommendation: A Distribution Shift Perspective
链接:https://www.aminer.cn/pub/64af9a083fda6d7f065a6db2/
18.Who Should Be Given Incentives? Counterfactual Optimal Treatment Regimes Learning for Recommendation
链接:https://www.aminer.cn/pub/64af9a083fda6d7f065a6dd5/
如何使用ChatPaper读文献?
为了让更多科研人更高效的获取文献知识,AMiner基于GLM-130B大模型能力,开发了Chatpaper,帮助科研人快速提高检索、阅读论文效率,获取最新领域研究动态,让科研工作更加游刃有余。
ChatPaper是一款集检索、阅读、知识问答于一体的对话式私有知识库,AMiner希望通过技术的力量,让大家更加高效地获取知识。
ChatPaper:https://www.aminer.cn/chat/g
KDD顶会入口:https://www.aminer.cn/conf/5ea1b22bedb6e7d53c00c41b/KDD2023