CIKM2020推荐系统论文集合

作者 | 学派

链接 | https://zhuanlan.zhihu.com/p/261077109

编辑 | 机器学习与推荐算法

CIKM2020(http://www.cikm2020.org/)是数据挖掘相关领域一大盛会，将于10月召开，相关论文列表已经放出。下面对本次接收的推荐系统论文进行了筛选和整理。按照推荐系统中的应用场景可以大致划分为：CTR预估、序列推荐、文本类推荐、Job推荐、社交推荐、Bundle推荐等。同时，GNN、知识图谱、知识蒸馏、强化学习、迁移学习、AutoML在推荐系统的落地应用也成为当下的主要研究点。从工业界参会来看，CIKM2020明显不如KDD2020，主要集中在国内大厂包括阿里、华为、百度、平安等，国外厂商少见。

CTR Prediction

1. Deep Time-Aware Item Evolution Network for Click-Through Rate Prediction

2. 【阿里、蚂蚁金服】MTBRN: Multiplex Target-Behavior Relation Enhanced Network for Click-Through Rate Prediction

论文：arxiv.org/abs/2008.0567

3. Deep Multi-Interest Network for Click-through Rate Prediction

4. 【阿里】MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction

论文：arxiv.org/abs/2008.0297

5. 【阿里】Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-through Rate Prediction

论文：arxiv.org/abs/2006.0563

6. Dimension Relation Modeling for Click-Through Rate Prediction

7. 【华为】AutoFeature: Searching for Feature Interactions and Their Architectures for Click-through Rate Prediction

8. 【华为】Ensembled CTR Prediction via Knowledge Distillation

GNN based Recommendation

1.【华为】TGCN: Tag Graph Convolutional Network for Tag-Aware Recommendation

2. Star Graph Neural Networks for Session-based Recommendation

3. DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation

4. Multiplex Graph Neural Networks for Multi-behavior Recommendation

5. Time-aware Graph Relational Attention Network for Stock Recommendation

6. 【华为】GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems

论文：arxiv.org/abs/2008.1351

7. Graph Neural Network for Tag Ranking in Tag-enhanced Video Recommendation

8. Decoupled Graph Convolution Network for Inferring Substitutable and Complementary Items

论文：https://github.com/guyulongcs/CIKM2020_DecGCN...
代码：guyulongcs/CIKM2020_DecGCN

Knowledge Graph-enhanced Recommendation

1. News Recommendation with Topic-Enriched Knowledge Graphs

2. Multi-modal Knowledge Graphs for Recommender Systems

论文：zheng-kai.com/paper/cik

3. CAFE: Coarse-to-Fine Knowledge Graph Reasoning for E-Commerce Recommendation

4. MindReader: Recommendation over Knowledge Graph Entities with Explicit User Ratings

论文：https://people.cs.aau.dk/~matteo/publications...

Sequential Recommendation

1. Hybrid Sequential Recommender via Time-aware Attentive Memory Network

2. Improving End-to-End Sequential Recommendations with Intent-aware Diversification

3. Quaternion-based self-Attentive Long Short-term User Preference Encoding for Recommendation

4. Star Graph Neural Networks for Session-based Recommendation

5. S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

Text-based Recommendation

1. Set-Sequence-Graph: A Multi-View Approach Towards Exploiting Reviews for Recommendation

2. TPR: Text-aware Preference Ranking for Recommender Systems

3. News Recommendation with Topic-Enriched Knowledge Graphs

4. Transformer Models for Recommending Related Questions in Web Search

Job Recommendation

1.【BOSS直聘】Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

论文：arxiv.org/abs/2009.1329

2. 【平安】Learning Effective Representations for Person-Job Fit by Feature Fusion

论文：arxiv.org/abs/2006.0701

Location-based Recommendation

1. STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendation

2. Learning Graph-Based Geographical Latent Representation for Point-of-Interest Recommendation

3. Magellan: A Personalized Travel Recommendation System Using Transaction Data

Social Recommendation

1. Partial Relationship Aware Influence Diffusion via Multi-channel Encoding Scheme for Social Recommendation

2. DREAM: A Dynamic Relation-Aware Model for social recommendation

Ranking/Re-ranking

1.【华为】Personalized Re-ranking with Item Relationships for E-commerce

2. Personalized Flight Itinerary Ranking at Fliggy

3. Deep Multifaceted Transformers for Multi-objective Ranking in Large-Scale E-commerce Recommender Systems

4. 【华为】U-rank: Utility-oriented Learning to Rank with Implicit Feedback

5. E-commerce Recommendation with Weighted Expected Utility

Recommendation Diversity

1. ART (Attractive Recommendation Tailor): How the Diversity of Product Recommendations Affects Customer Purchase Preference in Fashion Industry?

2. P-Companion: A Principled Framework for Diversified Complementary Product Recommendation

Explainable Recommendation

1. Explainable Recommender Systems via Resolving Learning Representations

2. Generating Neural Template Explanations for Recommendation

User Profiling

1. Ranking User Attributes for Fast Candidate Selection in Recommendation Systems

2. Learning to Build User-tag Profile in Recommendation System

3. Masked-field Pre-training for User Intent Prediction

Online Advertising

1. Representative Negative Instance Generation for Online Ad Targeting

2. 【Yahoo】Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement

论文：arxiv.org/abs/2008.0746

3. 【阿里】A Deep Prediction Network for Understanding Advertiser Intent and Satisfaction

论文：arxiv.org/pdf/2008.0893

Knowledge Distillation for Recommendation

1. DE-RRD: A Knowledge Distillation Framework for Recommender System

2. 【华为】Ensembled CTR Prediction via Knowledge Distillation

AutoML for Recommendation

2.【华为】AutoFeature: Searching for Feature Interactions and Their Architectures for Click-through Rate Prediction

RL for Recommendation

1. 【百度】Whole-Chain Recommendations

论文：Whole-Chain Recommendations

Cold-Start and Transfer Learning

1. Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval

2. Dual Autoencoder Network with Swap Reconstruction for Cold-Start Recommendation

3. Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks

4. 【阿里】MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction

论文：arxiv.org/abs/2008.0297

Bundle/Group Recommendation

1. Personalized Bundle Recommendation in Online Game

Debiasing

1. Feedback Loop and Bias Amplification in Recommender Systems

2. Exploring Missing Interactions: A Convolutional Generative Adversarial Network for Collaborative Filtering

Evaluation

1. Critically Examining the Claimed Value of Convolutions over User-Item Embedding Maps for Recommender Systems

2. Revisiting Alternative Experimental Settings for Evaluating Top-N Item Recommendation Algorithms

3. LensKit for Python: Next-Generation Software for Recommender Systems Experiments

New Scenarios

1. 【阿里】EdgeRec: Recommender System on Edge in Mobile Taobao

2. Leveraging Historical Interaction Data for Improving Conversational Recommender System

Others

1. Live Multi-Streaming and Donation Recommendations via Coupled Donation-Response Tensor Factorization

推荐阅读

围观RecSys2020 | 推荐系统顶会说了啥？(附论文打包下载)