WSDM 2022

182 papers
The 2022 edition of WSDM featured 279 papers centered on advancements in information retrieval and data mining. A primary focus was the refinement of recommendation systems, with research addressing sequential recommendation, cold-start personalization, and the mitigation of representation collapse. Contrastive learning and intent-preserving data augmentation emerged as key methodologies for improving these systems. The program also emphasized robust evaluation and learning frameworks, including counterfactual evaluation of decision-making policies and doubly robust off-policy evaluation for ranking. Other research directions included unbiased learning to rank from biased user interactions and the application of variational autoencoders for collaborative filtering. Technical explorations extended to graph-based learning, relational triple extraction, and the analysis of co-evolving sequences. Prolific contributors to this year's proceedings included Suhang Wang, Ruocheng Guo, and Leyu Lin. Additionally, the conference addressed social challenges through tutorials on combating online hate speech by examining content, psychology, and user behavior.

Top Research Directions

Research directions most represented by WSDM 2022 papers.

Dynamic Preference Modeling in Interactive Systems 7
The Pareto Frontier of Algorithmic Accuracy and Fairness 3
Mitigating Popularity Bias in Recommender Systems 3
Self Supervised Regularization for Sparse Recommender Systems 3
Mitigating the Cold Start Problem in Recommender Systems 3
Modeling Heterogeneous Behaviors in Recommender Systems 2
Data Poisoning and Shilling in Recommender Systems 2
Multimodal Feature Fusion for Recommender Systems 2
Task-Dependent Graph Topology 1
The Robustness Costs of Model Complexity 1
Bidirectional Search for Relational Extraction 1
Parameter Efficient Knowledge Graph Embeddings 1
Managing the Precision Recall Tradeoff in Information Extraction 1
Accelerating Neural Inference via Precomputed Lookup Tables 1
Behavioral Model Mismatch in Learning to Rank 1

Top Authors

AuthorPapers
Huan Liu4
Ruocheng Guo4
Suhang Wang4
Dawei Yin3
Ido Guy3
Min Zhang3
Neil Shah3
Ruobing Xie3
Shaoping Ma3
Tanmoy Chakraborty3
xiuqiang He3
Yanghua Xiao3
Yiqun LIU3
Yongfeng Zhang3
Zhicheng Dou3
Alexandros Karatzoglou2
Ambuj Singh2
Bo Zheng2
Chuan Shi2
Enyan Dai2

Impactful Papers

Papers from WSDM 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Search and Discovery in Personal Email Collections
Self-supervised Graph Representation Learning for Black Market Account Detection
Semi-supervised Stance Detection of Tweets Via Distant Network Supervision
Sentiment Analysis of Fashion Related Posts in Social Media
Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce
Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations
Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations
Stochastic Solutions for Dense Subgraph Discovery in Multilayer Networks
Structure Meets Sequences: Predicting Network of Co-evolving Sequences
Supervised Advantage Actor-Critic for Recommender Systems
Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks
S-Walk: Accurate and Scalable Session-based Recommendation with Random Walks
The Datasets Dilemma: How Much Do We Really Know About Recommendation Datasets?
The Multi-vehicle Ride-Sharing Problem
The Pit Stop Problem: How to Plan Your Next Road Trip
Time Masking for Temporal Language Models
Toward Pareto Efficient Fairness-Utility Trade-off in Recommendation through Reinforcement Learning
Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features
Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels
Towards Unbiased and Robust Causal Ranking for Recommender Systems
Translating Human Mobility Forecasting through Natural Language Generation
Triangle Graph Interest Network for Click-through Rate Prediction
Unbiased Knowledge Distillation for Recommendation
Uncovering Causal Effects of Online Short Videos on Consumer Behaviors
Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective
Understanding and Mitigating the Effect of Outliers in Fair Ranking
Unsupervised Cross-Domain Adaptation for Response Selection Using Self-Supervised and Adversarial Training
Using Conjunctions for Faster Disjunctive Top-k Queries
VAE++: Variational AutoEncoder for Heterogeneous One-Class Collaborative Filtering
Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation
Web Search via an Efficient and Effective Brain-Machine Interface
Wikipedia Reader Navigation: When Synthetic Data Is Enough

« prev Page 4/4