【KDD 2020】推荐系统领域论文汇总

点击上方，选择星标或置顶，不定期资源大放送！

阅读大概需要9分钟

Follow小博主，每天更新前沿干货

【导读】本文为大家收集整理了KDD 2020 会议上推荐系统方面的一些论文汇总。

ACM SIGKDD（国际数据挖掘与知识发现大会，简称KDD）是数据科学界最重要的会议，由ACM的数据挖掘及知识发现专委会（SIGKDD）主办，是CCF A类会议。每年大会都汇聚了来自数据科学、数据挖掘、知识发现、大规模数据分析和大数据的研究人员和从业者。自 1995 年以来，KDD 已经连续举办了二十余届大会，今年是第26届。今年的 KDD 大会将于 2020 年 8 月 23 日 ~27 日在美国美国加利福尼亚州圣地亚哥举行。其中今年的Research Track接受率为216/1279=16.8%。

论文链接：https://www.kdd.org/kdd2020/accepted-papers

推荐系统论文列表

这次整理的推荐系统论文列表分为了Research Track和Applied Data Science Track，即面向研究型的学术论文和面向工业界的实践论文。

Research Track Papers

研究赛道的论文主要是按照推荐子领域来划分，比如序列化推荐、对话推荐系统、冷启动问题、协同过滤、推荐效率问题等。从以下比例可以看出，序列化推荐和对话推荐系统是研究的热点问题，这其实也很容易理解，推荐其实是个天然的序列问题，即建模用户的一系列行为同时返回一系列个性化的物品序列；同时，推荐系统也自然的引入对话机制，因为传统的推荐是静态的，用户只能被动的接受着推荐系统返回的结果列表，引入对话交互机制后，能很好的优化推荐系统。

1. Disentangled Self-Supervision in Sequential Recommenders

Authors: Jianxin Ma: Alibaba Group; Tsinghua University; Chang Zhou: Alibaba Group; Hongxia Yang: Alibaba Group; Cui Peng: Tsinghua University; Xin Wang: Tsinghua University; Wenwu Zhu: Tsinghua University

阿里巴巴在本文提出了一种让机器更懂人类的方法，可实现长远预测。该论文提出预测人类行为的训练思路，融合解纠缠表征的技术和自监督对比学习技术，突破了目前主流推荐算法依赖于过往数据做预测而无法进行精准、长远推理的局限。

2.Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions

Authors: James McInerney: Netflix; Brian Brost: Spotify; Praveen Chandar: Spotify; Rishabh Mehrotra: Spotify; Ben Carterette: Spotif

3. Geography-Aware Sequential Location Recommendation

Authors: Defu Lian: University of Science and Technology of China; Yongji Wu: University of Science and Technology of China; Yong Ge: University of Arizona; Xing Xie: Microsoft Research Asia; Enhong Chen: University of Science and Technology of China

4. Handling Information Loss of Graph Neural Networks for Session-based Recommendation

Authors: Tianwen Chen: The Hong Kong University of Science and Technology; Raymond Chi-Wing Wong: The Hong Kong University of Science and Technology

5. On Sampling Top-K Recommendation Evaluation

Authors: Dong Li: Kent State University; Ruoming Jin: Kent State University; Jing Gao: iLambda; Zhi Liu: iLambda

6. Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation

Authors: Chen Ma: McGill University; Liheng Ma: McGill University; Yingxue Zhang: Huawei Technologies Canada; Ruiming Tang: Huawei Noah's Ark Lab; Xue Liu: McGill University; Mark Coates: McGill University

7. Evaluating Conversational Recommender Systems via User Simulation

Authors: Shuo Zhang: University of Stavanger; Krisztian Balog: University of Stavanger

8. Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion

Authors: Kun Zhou: Peking University; Xin Zhao: Renmin University of China, School of Information; Shuqing Bian: Renmin University of China; Yuanhang Zhou: Xidian University; Ji-Rong Wen: Renmin University; Jingsong Yu: Peking University

9. Interactive Path Reasoning on Graph for Conversational Recommendation

Authors: Wenqiang Lei: National University of Singapore; Gangyi Zhang: University of Science and Technology of China; Xiangnan He: University of Science and Technology of China; Yisong Miao: National University of Singapore; Xiang Wang: National University of Singapore; Liang Chen: Sun Yat-Sen University; Tat-Seng Chua: National University of Singapore

10. MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation

Authors: Manqing Dong: University of New South Wales; Feng Yuan: University of New South Wales; Lina Yao: University of New South Wales; Xiwei Xu: Data 61; Liming Zhu: Data 61

11. Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation

Authors: Yuanfu Lu: Beijing University of Posts and Telecommunications; Yuan Fang: Singapore Management University; Chuan Shi: Beijing University of Posts and Telecommunications

12. Dual Channel Hypergraph Collaborative Filtering

Authors: Shuyi Ji: Tsinghua University; Yifan Feng: Xiamen University; Rongrong Ji: Xiamen University; Xibin Zhao: Tsinghua University; Wanwan Tang: Baidu, Inc.; Yue Gao: Tsinghua University

13. Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation

Authors: Wenhui Yu: Tsinghua University; Xiao Lin: Alibaba Group; Junfeng Ge: Alibaba Group; Wenwu Ou: Alibaba Group; Zheng Qin: Tsinghua University

14. An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph

Authors: Jiarui Jin: Shanghai Jiao Tong University; Jiarui Qin: Shanghai Jiao Tong University; Yuchen Fang: Shanghai Jiao Tong University; Kounianhua Du: Shanghai Jiao Tong University; Weinan Zhang: Shanghai Jiao Tong University; Yong Yu: Shanghai Jiao Tong University; Zheng Zhang: Amazon; Alexander Smola: Amazon

15. Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems

Authors: Hao-Jun Shi: Northwestern University; Dheevatsa Mudigere: Facebook; Maxim Naumov: Facebook; Jiyan Yang: Facebook

16. FedFast: Going Beyond Average for Faster Training of Federated Recommender Systems

Authors: Khalil Muhammad: Insight Centre for Data Analytics, University College Dublin; Qinqin Wang: Insight Centre for Data Analytics, University College Dublin; Diarmuid O' Reilly-Morgan: Insight Centre for Data Analytics, University College Dublin; Elias Tragos: Insight Centre for Data Analytics, University College Dublin; Barry Smyth: Insight Centre for Data Analytics, University College Dublin; Neil Hurley: Insight Centre for Data Analytics, University College Dublin; James Geraci: Samsung Electronics; Aonghus Lawlor: Insight Centre for Data Analytics, University College Dublin

17. A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks

Authors: Jianing Sun: Huawei Technologies Canada; Wei Guo: Huawei Noah's Ark Lab; Dengcheng Zhang: Huawei Distributed and Parallel Software Lab; Yingxue Zhang: Huawei Technologies Canada; Florence Robert-Regol: McGill University; Yaochen Hu: Huawei Technologies Canada; Huifeng Guo: Huawei Noah's Ark Lab; Ruiming Tang: Huawei Noah's Ark Lab; Han Yuan: Huawei Distributed and Parallel Software Lab; Xiuqiang He: Huawei Noah's Ark Lab; Mark Coates: McGill University

18. BLOB: A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals

Authors: Otmane Sakhi: Criteo; Stephen Bonner: Durham University; David Rohde: Criteo; Flavian Vasile: Criteo

19. Joint Policy-Value Learning for Recommendation

Authors: Olivier Jeunen: University of Antwerp; David Rohde: Criteo; Flavian Vasile: Criteo; Martin Bompaire: Criteo

20. On Sampled Metrics for Item Recommendation

Authors: Walid Krichene: Google; Steffen Rendle: Google

Applied Data Science Track Papers

应用数据科学赛道主要是展示工业界中的实践成果，我们按照公司维度整理出了涉及推荐场景的论文，其中包括谷歌、阿里、亚马逊等公司，这些公司由于有着海量的用户数据，因此推荐技术也相对成熟，许多经典模型也是由以下公司所提出的。

1. Google

• Attribute-based Propensity for Unbiased Learning in Recommender Systems: Algorithm and Case Studies

• Improving Recommendation Quality in Google Drive

• Neural Input Search for Large Scale Recommendation Models

2. Alibaba

• Controllable Multi-Interest Framework for Recommendation

• M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems

• Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective

• Privileged Features Distillation at Taobao Recommendations -Alibaba

3. Amazon

• Temporal-Contextual Recommendation in Real-Time

4. Pinterest

• PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest -Pinterest

5. Bytedance

• Jointly Learning to Recommend and Advertise -Bytedance

6. DiDiChuxing

• Gemini: A novel and universal heterogeneous graph information fusing framework for online recommendations

7. Twitter

• SimClusters: Community-Based Representations for Heterogeneous Recommendations at Twitter

欢迎添加群助手微信，邀请您加入大佬云集-机器学习技术交流群！

???? 长按识别添加，邀请您进群！