CIKM 2021

447 papers

Top Research Directions

Research directions most represented by CIKM 2021 papers.

Self Supervised Regularization for Sparse Recommender Systems 6
Dynamic Preference Modeling in Interactive Systems 6
Mitigating the Cold Start Problem in Recommender Systems 5
Standardizing Evaluation Protocols in Machine Learning 4
Over-Smoothing in Graph Neural Networks 4
Cross Domain Generalization in Recommender Systems 3
Unified Evaluation Frameworks for Reproducible Machine Learning 3
Reconstructing Private Data from Model Gradients 3
Meta Path Learning in Heterogeneous Networks 2
Deep Learning for Spatiotemporal Flow Forecasting 2
Model-Agnostic Interpretability for Black-Box Systems 2
Learning Individual Treatment Effects Under Counterfactual Unobservability 2
Random Initialization Variance in Deep Learning 2
Decoupled Modular Frameworks for Rapid Scientific Experimentation 2
Continuous Time Latent Dynamics with Neural ODEs 2

Top Authors

AuthorPapers
Philip S. Yu8
Jun Zhou7
Hongzhi Yin6
Ji-Rong Wen6
JUN ZHOU6
Ping Li6
Yiqun LIU6
Bo Zheng5
Jundong Li5
Kai Zheng5
Liang Wang5
Shu Wu5
Wenjie Zhang5
xiuqiang He5
Xu Chen5
Xueqi Cheng5
Zhicheng Dou5
Zhiqiang Zhang5
Avi Caciularu4
Chuan Shi4

Impactful Papers

Papers from CIKM 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Hyperbolic Hypergraphs for Sequential Recommendation
HyperGraph Convolution Based Attributed HyperGraph Clustering
Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization
iMap: Incremental Node Mapping between Large Graphs Using GNN
IMAS++: An Intelligent Medical Analysis System Enhanced with Deep Graph Neural Networks
Improving Chinese Character Representation with Formation Graph Attention Network
Improving Irregularly Sampled Time Series Learning with Time-Aware Dual-Attention Memory-Augmented Networks
Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback
Incorporating Query Reformulating Behavior into Web Search Evaluation
Incremental Graph Convolutional Network for Collaborative Filtering
Inductive Matrix Completion Using Graph Autoencoder
Influence-guided Data Augmentation for Neural Tensor Completion
Integrating Pattern- and Fact-based Fake News Detection via Model Preference Learning
Integrating Transductive and Inductive Embeddings Improves Link Prediction Accuracy
International Workshop on Privacy, Security and Trust in Computational Intelligence (PSTCI2021)
Interpreting Convolutional Sequence Model by Learning Local Prototypes with Adaptation Regularization
Into the Unobservables: A Multi-range Encoder-decoder Framework for COVID-19 Prediction
Is a Single Model Enough? MuCoS: A Multi-Model Ensemble Learning Approach for Semantic Code Search
Jasmine: Exploring the Dependency-Aware Execution on Distributed Shared Memory
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance
Jura: Towards Automatic Compliance Assessment for Annual Reports of Listed Companies
K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering
L2NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning
Label-informed Graph Structure Learning for Node Classification
Large-scale Secure XGB for Vertical Federated Learning
LC: A Flexible, Extensible Open-Source Toolkit for Model Compression
Learning An End-to-End Structure for Retrieval in Large-Scale Recommendations
Learning Discriminative and Unbiased Representations for Few-Shot Relation Extraction
Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation
Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
Learning Ideological Embeddings from Information Cascades
Learning Implicit User Profile for Personalized Retrieval-Based Chatbot
Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images
Learning Multiple Intent Representations for Search Queries
Learning Representations of Inactive Users: A Cross Domain Approach with Graph Neural Networks
Learning Saliency Maps to Explain Deep Time Series Classifiers
Learning Sparse Binary Code for Maximum Inner Product Search
Learning to Augment Imbalanced Data for Re-ranking Models
Learning to Cluster via Same-Cluster Queries
Learning to Expand: Reinforced Response Expansion for Information-seeking Conversations
Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction
Learning to Pack: A Data-Driven Tree Search Algorithm for Large-Scale 3D Bin Packing Problem
LEReg: Empower Graph Neural Networks with Local Energy Regularization
Leveraging Domain Information to Classify Financial Documents via Unsupervised Graph Momentum Contrast
Leveraging the Graph Structure of Neural Network Training Dynamics
librec-auto: A Tool for Recommender Systems Experimentation
LightMove: A Lightweight Next-POI Recommendation forTaxicab Rooftop Advertising
Lightweight Self-Attentive Sequential Recommendation
Lightweight Visual Question Answering using Scene Graphs
LiteGT: Efficient and Lightweight Graph Transformers

« prev Page 5/9 next »