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
On Swap Convexity of Voting Rules
On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models
On the Convergence of Model Free Learning in Mean Field Games
On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning
On the Expressivity of ASK Queries in SPARQL
On the Generation of Medical Question-Answer Pairs
On the Hierarchical Information in a Single Contextualised Word Representation (Student Abstract)
On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks
On the Max-Min Fair Stochastic Allocation of Indivisible Goods
On the Parameterized Complexity of Clustering Incomplete Data into Subspaces of Small Rank
On the Problem of Covering a 3-D Terrain
On the Robustness of Face Recognition Algorithms Against Attacks and Bias
On the Role of Weight Sharing During Deep Option Learning
OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization
Open Domain Event Text Generation
Opening the Black Box: Automatically Characterizing Software for Algorithm Selection (Student Abstract)
Open-World Learning for Radically Autonomous Agents
Optical Flow in Deep Visual Tracking
Optimal Attack against Autoregressive Models by Manipulating the Environment
Optimal Auction Based Automated Negotiation in Realistic Decentralised Market Environments
Optimal Common Contract with Heterogeneous Agents
Optimal Exploration Algorithm of Multi-Agent Reinforcement Learning Methods (Student Abstract)
Optimal Feature Transport for Cross-View Image Geo-Localization
Optimal Margin Distribution Learning in Dynamic Environments
Optimization of Chance-Constrained Submodular Functions
Optimizing Discrete Spaces via Expensive Evaluations: A Learning to Search Framework
Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization Offers Significant Performance and Efficiency Gains
Optimizing Reachability Sets in Temporal Graphs by Delaying
Optimizing the Feature Selection Process for Better Accuracy in Datasets with a Large Number of Features (Student Abstract)
Options of Interest: Temporal Abstraction with Interest Functions
Order-Free Learning Alleviating Exposure Bias in Multi-Label Classification
Order Matters: Semantic-Aware Neural Networks for Binary Code Similarity Detection
Outlier Detection Ensemble with Embedded Feature Selection
Overcoming Catastrophic Forgetting by Neuron-Level Plasticity Control
Overcoming Language Priors in VQA via Decomposed Linguistic Representations
OVL: One-View Learning for Human Retrieval
Pairwise Fairness for Ranking and Regression
Pairwise Learning with Differential Privacy Guarantees
Parallel AND/OR Search for Marginal MAP
ParamE: Regarding Neural Network Parameters as Relation Embeddings for Knowledge Graph Completion
Parameterised Resource-Bounded ATL
Parameterized Algorithms for Finding a Collective Set of Items
Parameterized Complexity of Envy-Free Resource Allocation in Social Networks
Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning
Parsing as Pretraining
Partial Correlation-Based Attention for Multivariate Time Series Forecasting
Partial Label Learning with Batch Label Correction
Partial Multi-Label Learning with Label Distribution
Partial Multi-Label Learning with Noisy Label Identification
Particle Filter Recurrent Neural Networks

« prev Page 27/39 next »