WSDM 2024

136 papers
The 2024 edition of WSDM featured 209 papers, with a focus on addressing biases in recommendation systems and information retrieval. Research themes included correcting exposure and popularity bias through multifactorial causal debiasing and distributionally robust optimization. Considerable attention was given to differentiable ranking and sorting via continuous relaxations, as well as representation learning techniques designed to mitigate representation collapse and improve long-tail recommendations. The conference also included work on sequential recommendation using linear recurrent units, adapter-based transfer learning, and multi-line mathematical formula recognition. Methodological developments involved meta-bootstrapping for link prediction and mixed censored multi-task learning for price prediction. Prolific authors contributing to the year's proceedings included Hao Peng, Philip S. Yu, Qishen Zhang, and Zhongyi Liu. The collected research highlights a trend toward improving the reliability and efficiency of high-dimensional learning models and unbiased learning to rank applications.

Top Research Directions

Research directions most represented by WSDM 2024 papers.

Mitigating Popularity Bias in Recommender Systems 3
Reducing the Memory and Latency of Language Model Inference 3
Differentiable Relaxations for Sorting and Ranking 2
Graph Neural Networks under Distribution Shift 2
Scaling Graph Neural Networks to Massive Datasets 2
Unifying Self-Supervised Learning via Spectral and Information Theory 1
Preventing Label Leakage in Graph Neural Networks 1
Gradient Based Exploration in Neural Contextual Bandits 1
Topology Constrained Sampling for Graph Embeddings 1
The Connectivity Noise Tradeoff in Similarity Graphs 1
Preventing Rank Collapse in Deep Representations 1
The Generative Capability Gap in Bidirectional Transformers 1
Non Uniform Embedding Dimension Allocation 1
Frequency Aware Embedding Allocation 1
Learning Causal World Models Through Active Intervention 1

Top Authors

AuthorPapers
Hao Peng4
Ruiming Tang4
Guannan Zhang3
Hongzhi Yin3
Jun Zhou3
JUN ZHOU3
Philip S. Yu3
Qishen Zhang3
Rui Zhang3
Yang Song3
Adam Jatowt2
Amin Beheshti2
Anoop Deoras2
Binbin Hu2
Bo Zheng2
Branislav Kveton2
Chen Gao2
Chengyu Wang2
Chenliang Li2
Chen Wang2

Impactful Papers

Papers from WSDM 2024 that shaped research clusters.

Influential

Papers

Title
ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees
Psychology-informed Information Access Systems Workshop
Ranking with Long-Term Constraints
RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysis
Real-time E-bike Route Planning with Battery Range Prediction
Rethinking and Simplifying Bootstrapped Graph Latents
Revisiting Fake News Detection: Towards Temporality-aware Evaluation by Leveraging Engagement Earliness
SCAD: Subspace Clustering based Adversarial Detector
Scaling Up LLM Reviews for Google Ads Content Moderation
S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain
Source Free Graph Unsupervised Domain Adaptation
SSLRec: A Self-Supervised Learning Framework for Recommendation
Strategic ML: How to Learn With Data That 'Behaves'
Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study
Temporal Blind Spots in Large Language Models
Temporal Graph Analysis with TGX
TemporalMed: Advancing Medical Dialogues with Time-Aware Responses in Large Language Models
Text-Video Retrieval via Multi-Modal Hypergraph Networks
The 3rd International Workshop on Interactive and Scalable Information Retrieval Methods for eCommerce (ISIR-eCom 2024)
The 5th International Workshop on Machine Learning on Graphs (MLoG)
The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation
To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders
Towards Alignment-Uniformity Aware Representation in Graph Contrastive Learning
Towards Better Chinese Spelling Check for Search Engines: A New Dataset and Strong Baseline
Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
Towards Trustworthy Large Language Models
TTC-QuAli: A Text-Table-Chart Dataset for Multimodal Quantity Alignment
Unbiased Learning to Rank: On Recent Advances and Practical Applications
Unified Pretraining for Recommendation via Task Hypergraphs
Unified Visual Preference Learning for User Intent Understanding
User Behavior Enriched Temporal Knowledge Graphs for Sequential Recommendation
User Consented Federated Recommender System Against Personalized Attribute Inference Attack
Vector Search with OpenAI Embeddings: Lucene Is All You Need
Wildfire: A Twitter Social Sensing Platform for Layperson
WSDM 2024 Workshop on Large Language Models for Individuals, Groups, and Society
Your Causal Self-Attentive Recommender Hosts a Lonely Neighborhood

« prev Page 3/3