KDD 2020 推荐系统论文一览

作者 | 学派

链接 | https://zhuanlan.zhihu.com/p/161705748

编辑 | 深度传送门

KDD是推荐领域一个顶级的国际会议。本次接收的论文按照推荐系统应用场景可以大致划分为：CTR预估、TopN推荐、对话式推荐、序列推荐等。同时，GNN、强化学习、多任务学习、迁移学习、AutoML、元学习在推荐系统的落地应用也成为当下的主要研究点。此届会议有很大一部分来自工业界的论文，包括Google、Microsoft、Criteo、Spotify以及国内大厂阿里、百度、字节、华为、滴滴等。

CTR Prediction

1. AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction 【华为诺亚】

简介：本文采用AutoML的搜索方法选择重要性高的二次特征交互项、去除干扰项，提升FM、DeepFM这类模型的准确率。
论文：https://arxiv.org/abs/2003.11235

2. Category-Specific CNN for Visual-aware CTR Prediction at JD.com 【京东】

论文：https://arxiv.org/abs/2006.10337

3. Towards Automated Neural Interaction Discovering for Click-Through Rate Prediction 【Facebook】

论文：https://arxiv.org/abs/2007.06434

Graph-based Recommendation

1. A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks 【华为诺亚】

2. An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph 【Amazon】

论文：https://arxiv.org/abs/2007.00216

3. M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems 【阿里】

简介：本文通过关联多个视角的图(item-item图、item-shop图、shop-shop图等)增强item表征，用于item召回。
论文：https://arxiv.org/abs/2005.10110

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

5. Interactive Path Reasoning on Graph for Conversational Recommendation

论文：https://arxiv.org/abs/2007.00194

6. A Dual Heterogeneous Graph Attention Network to Improve Long-Tail Performance for Shop Search in E-Commerce 【阿里】

7. Gemini: A Novel and Universal Heterogeneous Graph Information Fusing Framework for Online Recommendations 【滴滴】

Conversational Recommendation

1. Evaluating Conversational Recommender Systems via User Simulation

论文：https://arxiv.org/abs/2006.08732

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

论文：https://arxiv.org/abs/2007.04032

3. Interactive Path Reasoning on Graph for Conversational Recommendation

论文：https://arxiv.org/abs/2007.00194

CF and Top-N Recommendation

1. Dual Channel Hypergraph Collaborative Filtering 【百度】

笔记：https://blog.csdn.net/weixin_42052231/article/details/107710301

2. Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation 【华为诺亚】

3. Controllable Multi-Interest Framework for Recommendation 【阿里】

论文：https://arxiv.org/abs/2005.09347

4. Embedding-based Retrieval in Facebook Search 【Facebook】

论文：https://arxiv.org/abs/2006.11632

5. On Sampling Top-K Recommendation Evaluation

Embedding and Representation

1. Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems 【Facebook】

论文：https://arxiv.org/abs/1909.02107

2. PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest 【Pinterest】

论文：https://arxiv.org/abs/2007.03634

3. SimClusters: Community-Based Representations for Heterogeneous Recommendations at Twitter 【Twitter】

4. Time-Aware User Embeddings as a Service 【Yahoo】

论文：https://astro.temple.edu/~tuf28053/papers/pavlovskiKDD20.pdf

Sequential Recommendation

1. Disentangled Self-Supervision in Sequential Recommenders 【阿里】

论文：http://pengcui.thumedialab.com/papers/DisentangledSequentialRecommendation.pdf

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

3. Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective 【阿里】

论文：https://arxiv.org/pdf/2006.04520.pdf

RL for Recommendation

1. Jointly Learning to Recommend and Advertise 【字节跳动】

论文：https://arxiv.org/abs/2003.00097

2. BLOB: A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals 【Criteo】

3. Joint Policy-Value Learning for Recommendation 【Criteo】

论文：https://www.researchgate.net/publication/342437800_Joint_Policy-Value_Learning_for_Recommendation

Multi-Task Learning

1. Privileged Features Distillation at Taobao Recommendations 【阿里】

论文：https://arxiv.org/abs/1907.05171

Transfer Learning

1. Learning Transferrable Parameters for Long-tailed Sequential User Behavior Modeling 【Salesforce】

2. Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation 【阿里】

论文：https://arxiv.org/abs/2007.07085

AutoML for Recommendation

1. Neural Input Search for Large Scale Recommendation Models 【Google】

论文：https://arxiv.org/abs/1907.04471

2. Towards Automated Neural Interaction Discovering for Click-Through Rate Prediction 【Facebook】

论文：https://arxiv.org/abs/2007.06434

Federated Learning

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

Evaluation

1. Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions 【Netflix, Spotify】

论文：https://arxiv.org/abs/2007.12986

2. Evaluating Conversational Recommender Systems via User Simulation

论文：https://arxiv.org/abs/2006.08732

3. On Sampled Metrics for Item Recommendation 【Google】

4. On Sampling Top-K Recommendation Evaluation

Debiasing

1. Debiasing Grid-based Product Search in E-commerce 【Etsy】

论文：http://www.public.asu.edu/~rguo12/kdd20.pdf

2. Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions 【Netflix, Spotify】

论文：https://arxiv.org/abs/2007.12986

3. Attribute-based Propensity for Unbiased Learning in Recommender Systems: Algorithm and Case Studies 【Google】

论文：https://research.google/pubs/pub49273/

POI Recommendation

1. Geography-Aware Sequential Location Recommendation 【Microsoft】

论文：http://staff.ustc.edu.cn/~liandefu/paper/locpred.pdf

Cold-Start Recommendation

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

论文：https://arxiv.org/abs/2007.03183

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

论文：https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=6158&context=sis_research

Others

1. Improving Recommendation Quality in Google Drive 【Google】

论文：https://research.google/pubs/pub49272/

2. Temporal-Contextual Recommendation in Real-Time 【Amazon】

论文：https://assets.amazon.science/96/71/d1f25754497681133c7aa2b7eb05/temporal-contextual-recommendation-in-real-time.pdf