KDD 2020

439 papers

Top Research Directions

Research directions most represented by KDD 2020 papers.

Self Supervised Regularization for Sparse Recommender Systems 5
Transparent Reasoning for Personalized Recommendation 4
Dynamic Preference Modeling in Interactive Systems 4
Integrating Negative Feedback into Recommender Systems 3
Multimodal Feature Fusion for Recommender Systems 3
The Information Loss of Hypergraph Clique Expansion 3
Neighborhood Size Sensitivity in Graph Construction 3
Adversarial Training for Domain Invariant Representations 3
Hypergraph to Graph Reduction 2
Generalized Cheeger Inequalities for Spectral Clustering 2
Proximity Graphs for High Dimensional Vector Search 2
Decoupled Representation Learning for Scalable Dense Retrieval 2
Hierarchical Learning Beyond Strict Tree Structures 2
Network Constrained Distance Modeling for Spatial Analysis 2
Progressive Sequence Length Training 2

Top Authors

AuthorPapers
Jiawei Han8
Peng Cui8
Hui Xiong6
Jian Pei5
Jieping Ye5
Jiliang Tang5
Aidong Zhang4
Jimeng Sun4
Jingrui He4
Shuiwang Ji4
Suhang Wang4
Yong Li4
Andrey Kan3
Chao Zhang3
Christos Faloutsos3
Donald Metzler3
Enhong Chen3
Fengli Xu3
Fenglong Ma3
Haifeng Wang3

Impactful Papers

Papers from KDD 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
TIMME: Twitter Ideology-detection via Multi-task Multi-relational Embedding
TinyGNN: Learning Efficient Graph Neural Networks
TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations
To Tune or Not to Tune?: In Search of Optimal Configurations for Data Analytics
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
Toward Responsible AI by Planning to Fail
Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction
Towards Building an Intelligent Chatbot for Customer Service: Learning to Respond at the Appropriate Time
Towards Deeper Graph Neural Networks
Towards Fair Truth Discovery from Biased Crowdsourced Answers
Towards Physics-informed Deep Learning for Turbulent Flow Prediction
TranSlider: Transfer Ensemble Learning from Exploitation to Exploration
Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes
Truth Discovery against Strategic Sybil Attack in Crowdsourcing
Tutorial on Human-Centered Explainability for Healthcare
Tutorial on Online User Engagement: Metrics and Optimization
Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning
Ultrafast Local Outlier Detection from a Data Stream with Stationary Region Skipping
Understanding Negative Sampling in Graph Representation Learning
Understanding the Impact of the COVID-19 Pandemic on Transportation-related Behaviors with Human Mobility Data
Understanding the Urban Pandemic Spreading of COVID-19 with Real World Mobility Data
Unleashing the Power of Subjective Data: Managing Experiences as First-Class Citizens
Unsupervised Differentiable Multi-aspect Network Embedding
Unsupervised Paraphrasing via Deep Reinforcement Learning
Unsupervised Translation via Hierarchical Anchoring: Functional Mapping of Places across Cities
USAD: UnSupervised Anomaly Detection on Multivariate Time Series
User Sentiment as a Success Metric: Persistent Biases Under Full Randomization
Using Machine Learning to Detect Cancer Early
Vamsa: Automated Provenance Tracking in Data Science Scripts
Voronoi Graph Traversal in High Dimensions with Applications to Topological Data Analysis and Piecewise Linear Interpolation
Vulnerability vs. Reliability: Disentangled Adversarial Examples for Cross-Modal Learning
WavingSketch: An Unbiased and Generic Sketch for Finding Top-k Items in Data Streams
WeightGrad: Geo-Distributed Data Analysis Using Quantization for Faster Convergence and Better Accuracy
What is that Building?: An End-to-end System for Building Recognition from Streetside Images
When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control
Why Attentions May Not Be Interpretable?
xGAIL: Explainable Generative Adversarial Imitation Learning for Explainable Human Decision Analysis
XGNN: Towards Model-Level Explanations of Graph Neural Networks
Z-Miner: An Efficient Method for Mining Frequent Arrangements of Event Intervals

« prev Page 9/9