No. 10: AAAI-21 Technical Tracks 10
AAAI Technical Track on Machine Learning III
Tempered Sigmoid Activations for Deep Learning with Differential Privacy
PDFVector Quantized Bayesian Neural Network Inference for Data Streams
PDFMaximum Roaming Multi-Task Learning
PDFFast PCA in 1-D Wasserstein Spaces via B-splines Representation and Metric Projection
PDFTop-k Ranking Bayesian Optimization
PDFDistributional Reinforcement Learning via Moment Matching
PDFPrecision-based Boosting
PDFImproving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries
PDFLearning of Structurally Unambiguous Probabilistic Grammars
PDFRT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
PDFWarm Starting CMA-ES for Hyperparameter Optimization
PDFInverse Reinforcement Learning From Like-Minded Teachers
PDFMultinomial Logit Contextual Bandits: Provable Optimality and Practicality
PDFLearning Deep Generative Models for Queuing Systems
PDFOT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport
PDFFC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting
PDFMeta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting
PDFAugmented Experiment in Material Engineering Using Machine Learning
PDFSecond Order Techniques for Learning Time-series with Structural Breaks
PDFDefending against Backdoors in Federated Learning with Robust Learning Rate
PDFRobustness Guarantees for Mode Estimation with an Application to Bandits
PDFDisentangled Information Bottleneck
PDFNASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search
PDFRobust Reinforcement Learning: A Case Study in Linear Quadratic Regulation
PDFPolicy Optimization as Online Learning with Mediator Feedback
PDFConsistency and Finite Sample Behavior of Binary Class Probability Estimation
PDFDiscovering Fully Oriented Causal Networks
PDFGenerative Semi-supervised Learning for Multivariate Time Series Imputation
PDFA General Class of Transfer Learning Regression without Implementation Cost
PDFScheduling of Time-Varying Workloads Using Reinforcement Learning
PDFImproved Mutual Information Estimation
PDFText-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
PDFTask-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate
PDFElastic Consistency: A Practical Consistency Model for Distributed Stochastic Gradient Descent
PDFGame of Gradients: Mitigating Irrelevant Clients in Federated Learning
PDFObjective-Based Hierarchical Clustering of Deep Embedding Vectors
PDF5* Knowledge Graph Embeddings with Projective Transformations
PDFAdvice-Guided Reinforcement Learning in a non-Markovian Environment
PDFClinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning
PDFModular Graph Transformer Networks for Multi-Label Image Classification
PDFDifferentially Private k-Means via Exponential Mechanism and Max Cover
PDFMinimum Robust Multi-Submodular Cover for Fairness
PDFTemporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecasting
PDFAn Information-Theoretic Framework for Unifying Active Learning Problems
PDFTailoring Embedding Function to Heterogeneous Few-Shot Tasks by Global and Local Feature Adaptors
PDFPULNS: Positive-Unlabeled Learning with Effective Negative Sample Selector
PDFRevisiting Co-Occurring Directions: Sharper Analysis and Efficient Algorithm for Sparse Matrices
PDFSemi-supervised Medical Image Segmentation through Dual-task Consistency
PDFAdaptive Knowledge Driven Regularization for Deep Neural Networks
PDFMulti-Domain Multi-Task Rehearsal for Lifelong Learning
PDFOn the Adequacy of Untuned Warmup for Adaptive Optimization
PDFLearning Representations for Incomplete Time Series Clustering
PDFJoint-Label Learning by Dual Augmentation for Time Series Classification
PDFUnsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
PDFSequential Attacks on Kalman Filter-based Forward Collision Warning Systems
PDFExact Reduction of Huge Action Spaces in General Reinforcement Learning
PDFComposite Adversarial Attacks
PDFDeep Mutual Information Maximin for Cross-Modal Clustering
PDFSearching for Machine Learning Pipelines Using a Context-Free Grammar
PDFScalable Graph Networks for Particle Simulations
PDFInfinite Gaussian Mixture Modeling with an Improved Estimation of the Number of Clusters
PDFExacerbating Algorithmic Bias through Fairness Attacks
PDFPhysarum Powered Differentiable Linear Programming Layers and Applications
PDFLenient Regret for Multi-Armed Bandits
PDFClass-Attentive Diffusion Network for Semi-Supervised Classification
PDFAuto-Encoding Transformations in Reparameterized Lie Groups for Unsupervised Learning
PDFMulti-Proxy Wasserstein Classifier for Image Classification
PDFTransTailor: Pruning the Pre-trained Model for Improved Transfer Learning
PDFLearning a Few-shot Embedding Model with Contrastive Learning
PDFUnchain the Search Space with Hierarchical Differentiable Architecture Search
PDFOvercoming Catastrophic Forgetting in Graph Neural Networks
PDFStable Adversarial Learning under Distributional Shifts
PDFHierarchical Multiple Kernel Clustering
PDFDynamically Grown Generative Adversarial Networks
PDFFLAME: Differentially Private Federated Learning in the Shuffle Model
PDFPost-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
PDFTrain a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
PDFROSITA: Refined BERT cOmpreSsion with InTegrAted techniques
PDFTask Aligned Generative Meta-learning for Zero-shot Learning
PDFLearning from eXtreme Bandit Feedback
PDFImproving Causal Discovery By Optimal Bayesian Network Learning
PDFStochastic Graphical Bandits with Adversarial Corruptions
PDFStochastic Bandits with Graph Feedback in Non-Stationary Environments
PDFDecentralized Policy Gradient Descent Ascent for Safe Multi-Agent Reinforcement Learning
PDFSynergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting
PDFBayesian Distributional Policy Gradients
PDFLearning Graph Neural Networks with Approximate Gradient Descent
PDFMulti-View Representation Learning with Manifold Smoothness
PDFBi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
PDFSublinear Classical and Quantum Algorithms for General Matrix Games
PDFA Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
PDFImproving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints
PDFMFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements
PDFLearned Extragradient ISTA with Interpretable Residual Structures for Sparse Coding
PDFOne-shot Graph Neural Architecture Search with Dynamic Search Space
PDFScheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Network
PDFOnline Optimal Control with Affine Constraints
PDFTRQ: Ternary Neural Networks With Residual Quantization
PDFContrastive Clustering
PDFLongitudinal Deep Kernel Gaussian Process Regression
PDFLarge Norms of CNN Layers Do Not Hurt Adversarial Robustness
PDFDoubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding
PDFFrom Label Smoothing to Label Relaxation
PDFSample Selection for Universal Domain Adaptation
PDF