AAAI 2020

1,923 papers

Top Research Directions

Research directions most represented by AAAI 2020 papers.

Adversarial Training for Domain Invariant Representations 16
The Sensitivity of Multi-Objective Loss Balancing 16
Pointer Generator Mechanisms for Grounded Text Generation 15
Modeling Label Dependencies in Multi-Label Learning 15
Graph Attention Mechanisms for Adaptive Feature Aggregation 15
Accelerating Neural Architecture Search Without Full Model Training 13
The Cross Modal Representation Gap 13
Dynamic Preference Modeling in Interactive Systems 13
Bypassing the Computational Bottleneck of Adversarial Training 13
Decomposing Context into Multi-Level Attention Hierarchies 12
Over-Smoothing in Graph Neural Networks 12
Mitigating Error Propagation in Pseudo Labeling 12
Iterative Model Assisted Labeling and Refinement 10
Overcoming Local Receptive Field Constraints in Visual Models 10
Maintaining Global Coherence in Long Form Text Generation 9

Top Authors

AuthorPapers
Rajiv Ratn Shah10
Hua Xu7
Min Yang7
Peter J. Stuckey7
Tat-Seng Chua7
Yi Yang7
Dongyan Zhao6
Houqiang Li6
Maosong Sun6
Yue Zhang6
Bohyung Han5
Chang Xu5
Chunyan Miao5
Enhong Chen5
Gan Sun5
Han Yu5
Iryna Gurevych5
Jie Zhou5
Milind Tambe5
Pin-Yu Chen5

Impactful Papers

Papers from AAAI 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Learning Agent Communication under Limited Bandwidth by Message Pruning
Learning and Reasoning for Robot Sequential Decision Making under Uncertainty
Learning Attentive Pairwise Interaction for Fine-Grained Classification
Learning-Based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching
Learning Conceptual-Contextual Embeddings for Medical Text
Learning Counterfactual Representations for Estimating Individual Dose-Response Curves
Learning Cross-Aligned Latent Embeddings for Zero-Shot Cross-Modal Retrieval
Learning Cross-Modal Context Graph for Visual Grounding
Learning Deep Relations to Promote Saliency Detection
Learning Directional Sentence-Pair Embedding for Natural Language Reasoning (Student Abstract)
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions
Learning Efficient Representations for Fake Speech Detection
Learning End-to-End Scene Flow by Distilling Single Tasks Knowledge
Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns
Learning Feature Interactions with Lorentzian Factorization Machine
Learning from Easy to Complex: Adaptive Multi-Curricula Learning for Neural Dialogue Generation
Learning from Interventions Using Hierarchical Policies for Safe Learning
Learning from Positive and Unlabeled Data without Explicit Estimation of Class Prior
Learning from the Past: Continual Meta-Learning with Bayesian Graph Neural Networks
Learning from Weak-Label Data: A Deep Forest Expedition
Learning General Latent-Variable Graphical Models with Predictive Belief Propagation
Learning Geo-Contextual Embeddings for Commuting Flow Prediction
Learning Graph Convolutional Network for Skeleton-Based Human Action Recognition by Neural Searching
Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
Learning Higher-Order Programs through Predicate Invention
Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume
Learning Light Field Angular Super-Resolution via a Geometry-Aware Network
Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption
Learning MAX-SAT from Contextual Examples for Combinatorial Optimisation
Learning Meta Model for Zero- and Few-Shot Face Anti-Spoofing
Learning Multi-Level Dependencies for Robust Word Recognition
Learning Multi-Modal Biomarker Representations via Globally Aligned Longitudinal Enrichments
Learning on the Job: Online Lifelong and Continual Learning
Learning Optimal Decision Trees Using Caching Branch-and-Bound Search
Learning Part Generation and Assembly for Structure-Aware Shape Synthesis
Learning Query Inseparable εℒℋ Ontologies
Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis
Learning Saliency-Free Model with Generic Features for Weakly-Supervised Semantic Segmentation
Learning Sense Representation from Word Representation for Unsupervised Word Sense Disambiguation (Student Abstract)
Learning Signed Network Embedding via Graph Attention
Learning Sparse Sharing Architectures for Multiple Tasks
Learning Student Networks with Few Data
Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer
Learning the Value of Teamwork to Form Efficient Teams
Learning to Auto Weight: Entirely Data-Driven and Highly Efficient Weighting Framework
Learning to Classify the Wrong Answers for Multiple Choice Question Answering (Student Abstract)
Learning to Communicate Implicitly by Actions
Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models
Learning to Crawl
Learning to Deblur Face Images via Sketch Synthesis

« prev Page 21/39 next »