KDD 2023

589 papers

Top Research Directions

Research directions most represented by KDD 2023 papers.

Overcoming the Homophily Assumption in Graph Neural Networks 7
Over-Smoothing in Graph Neural Networks 7
Dynamic Preference Modeling in Interactive Systems 7
Cross Domain Generalization in Recommender Systems 4
Learning on Graphs with Scarce Labels 4
The Weisfeiler Lehman Expressivity Bottleneck 4
Adapting Homogeneous Graph Learning to Heterogeneous Structures 4
Mitigating Short-Term Engagement Bias in Recommender Systems 4
Scaling Graph Learning to Massive Networks 4
Decoupling Local Community Structure from Global Graph Connectivity 3
Preserving Semantic Identity in Graph Contrastive Learning 3
Integrating Negative Feedback into Recommender Systems 3
Listwise Context and Inter Item Dependencies in Ranking 3
Beyond the Linear Assumption in Reward Modeling 3
Contamination Resistant Unsupervised Anomaly Detection 3

Top Authors

AuthorPapers
Hui Xiong12
Yong Li12
Bo Zheng9
Weinan Zhang9
Enhong Chen8
Jundong Li8
Junchi Yan7
Xing Xie7
Depeng Jin6
Dongmei Zhang6
Haifeng Chen6
Jie Tang6
Ruiming Tang6
Dawei Yin5
Hanghang Tong5
Huandong Wang5
Jian Xu5
Kun Gai5
Yuxiao Dong5
Aristides Gionis4

Impactful Papers

Papers from KDD 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
Spatial Clustering Regression of Count Value Data via Bayesian Mixture of Finite Mixtures
Spatial Heterophily Aware Graph Neural Networks
Spatio-temporal Diffusion Point Processes
Specify Robust Causal Representation from Mixed Observations
Sphere: Semi-Supervised Pre-training for Web Search over Heterogeneous Learning to Rank Data
Stabilising Job Survival Analysis for Disability Employment Services in Unseen Environments
Stationary Algorithmic Balancing For Dynamic Email Re-Ranking Problem
ST-iFGSM: Enhancing Robustness of Human Mobility Signature Identification Model via Spatial-Temporal Iterative FGSM
SURE: Robust, Explainable, and Fair Classification without Sensitive Attributes
Taming the Domain Shift in Multi-source Learning for Energy Disaggregation
Task-Equivariant Graph Few-shot Learning
Task Relation-aware Continual User Representation Learning
Temporal Dynamics-Aware Adversarial Attacks on Discrete-Time Dynamic Graph Models
Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data
Text Is All You Need: Learning Language Representations for Sequential Recommendation
The 12th International Workshop on Urban Computing
The 3rd Workshop on Artificial Intelligence-enabled Cybersecurity Analytics
The 3rd Workshop on Graph Learning Benchmarks (GLB 2023)
The 4th International Workshop on Talent and Management Computing (TMC'2023)
The 6th Workshop on e-eommerce and NLP (ECNLP 6)
The 9th SIGKDD International Workshop on Mining and Learning from Time Series
The Expressibility of Polynomial based Attention Scheme
The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles
The KDD'23 Workshop on Causal Discovery, Prediction and Decision (CDPD 2023)
The Missing Indicator Method: From Low to High Dimensions
Theoretical Convergence Guaranteed Resource-Adaptive Federated Learning with Mixed Heterogeneity
The Second Workshop on Applied Machine Learning Management
The Second Workshop on Knowledge-Augmented Methods for Natural Language Processing
Time-to-Event Modeling with Hypernetwork based Hawkes Process
Towards a Generic Framework for Mechanism-guided Deep Learning for Manufacturing Applications
Towards Disentangling Relevance and Bias in Unbiased Learning to Rank
Towards Equitable Assignment: Data-Driven Delivery Zone Partition at Last-mile Logistics
Towards Fair Disentangled Online Learning for Changing Environments
Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning
Towards Graph-level Anomaly Detection via Deep Evolutionary Mapping
Towards Next-Generation Intelligent Assistants Leveraging LLM Techniques
Towards Reliable Rare Category Analysis on Graphs via Individual Calibration
Towards Suicide Prevention from Bipolar Disorder with Temporal Symptom-Aware Multitask Learning
Towards Understanding and Enhancing Robustness of Deep Learning Models against Malicious Unlearning Attacks
Towards Variance Reduction for Reinforcement Learning of Industrial Decision-making Tasks: A Bi-Critic based Demand-Constraint Decoupling Approach
Training Large-scale Foundation Models on Emerging AI Chips
TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest
Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities
TransformerLight: A Novel Sequence Modeling Based Traffic Signaling Mechanism via Gated Transformer
Treatment Effect Estimation with Adjustment Feature Selection
Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation
TrustGeo: Uncertainty-Aware Dynamic Graph Learning for Trustworthy IP Geolocation
Trustworthy Machine Learning
Trustworthy Machine Learning: Robustness, Generalization, and Interpretability
Trustworthy Recommender Systems: Foundations and Frontiers

« prev Page 11/12 next »