No. 6: AAAI-22 Technical Tracks 6
AAAI Technical Track on Machine Learning I
Adaptive Kernel Graph Neural Network
PDFFully Spiking Variational Autoencoder
PDFNot All Parameters Should Be Treated Equally: Deep Safe Semi-supervised Learning under Class Distribution Mismatch
PDFWasserstein Unsupervised Reinforcement Learning
PDFMulti-Mode Tensor Space Clustering Based on Low-Tensor-Rank Representation
PDFToward Physically Realizable Quantum Neural Networks
PDFReinforcement Learning of Causal Variables Using Mediation Analysis
PDFAnytime Guarantees under Heavy-Tailed Data
PDFAdversarial Examples Can Be Effective Data Augmentation for Unsupervised Machine Learning
PDFTowards Automating Model Explanations with Certified Robustness Guarantees
PDFMulti-View Clustering on Topological Manifold
PDFAchieving Counterfactual Fairness for Causal Bandit
PDFUncertainty-Aware Learning against Label Noise on Imbalanced Datasets
PDFGlobally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes
PDFCausal Discovery in Hawkes Processes by Minimum Description Length
PDFGroup-Aware Threshold Adaptation for Fair Classification
PDFTowards Discriminant Analysis Classifiers Using Online Active Learning via Myoelectric Interfaces
PDFLabel Hallucination for Few-Shot Classification
PDFLearning Expected Emphatic Traces for Deep RL
PDFDelving into Sample Loss Curve to Embrace Noisy and Imbalanced Data
PDFFast Graph Neural Tangent Kernel via Kronecker Sketching
PDFCreativity of AI: Automatic Symbolic Option Discovery for Facilitating Deep Reinforcement Learning
PDFRecovering the Propensity Score from Biased Positive Unlabeled Data
PDFDiPS: Differentiable Policy for Sketching in Recommender Systems
PDFLearning Large DAGs by Combining Continuous Optimization and Feedback Arc Set Heuristics
PDFRegularized Modal Regression on Markov-Dependent Observations: A Theoretical Assessment
PDFPartial Multi-Label Learning via Large Margin Nearest Neighbour Embeddings
PDFLUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks
PDFSemi-supervised Conditional Density Estimation with Wasserstein Laplacian Regularisation
PDFGoTube: Scalable Statistical Verification of Continuous-Depth Models
PDFBalanced Self-Paced Learning for AUC Maximization
PDFTheoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods
PDFAdaptive Orthogonal Projection for Batch and Online Continual Learning
PDFLearning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks
PDFSelf-Supervised Pre-training for Protein Embeddings Using Tertiary Structures
PDFImproved Gradient-Based Adversarial Attacks for Quantized Networks
PDFTIGGER: Scalable Generative Modelling for Temporal Interaction Graphs
PDFA Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions
PDFOscillatory Fourier Neural Network: A Compact and Efficient Architecture for Sequential Processing
PDFEnd-to-End Probabilistic Label-Specific Feature Learning for Multi-Label Classification
PDFCross-Domain Few-Shot Graph Classification
PDFSpreadGNN: Decentralized Multi-Task Federated Learning for Graph Neural Networks on Molecular Data
PDFBayesian Optimization over Permutation Spaces
PDFMeta Propagation Networks for Graph Few-shot Semi-supervised Learning
PDFOnline Certification of Preference-Based Fairness for Personalized Recommender Systems
PDFDisentangled Spatiotemporal Graph Generative Models
PDFLearning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples
PDFAdaptive and Universal Algorithms for Variational Inequalities with Optimal Convergence
PDFZero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
PDFGradient Flow in Sparse Neural Networks and How Lottery Tickets Win
PDFDynamic Nonlinear Matrix Completion for Time-Varying Data Imputation
PDFUp to 100x Faster Data-Free Knowledge Distillation
PDFLearning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification
PDFKerGNNs: Interpretable Graph Neural Networks with Graph Kernels
PDFScaling Neural Program Synthesis with Distribution-Based Search
PDFModification-Fair Cluster Editing
PDFReinforcement Learning Based Dynamic Model Combination for Time Series Forecasting
PDFJFB: Jacobian-Free Backpropagation for Implicit Networks
PDFSmoothing Advantage Learning
PDFEnhancing Counterfactual Classification Performance via Self-Training
PDFLearning V1 Simple Cells with Vector Representation of Local Content and Matrix Representation of Local Motion
PDFAlgorithmic Concept-Based Explainable Reasoning
PDFASM2TV: An Adaptive Semi-supervised Multi-Task Multi-View Learning Framework for Human Activity Recognition
PDFIdentification of Linear Latent Variable Model with Arbitrary Distribution
PDFDPNAS: Neural Architecture Search for Deep Learning with Differential Privacy
PDFGraph Neural Controlled Differential Equations for Traffic Forecasting
PDFDifferentially Private Regret Minimization in Episodic Markov Decision Processes
PDFLearning by Competition of Self-Interested Reinforcement Learning Agents
PDFHow to Distribute Data across Tasks for Meta-Learning?
PDFSimilarity Search for Efficient Active Learning and Search of Rare Concepts
PDFLearning Influence Adoption in Heterogeneous Networks
PDFGraph-Wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning
PDFReinforcement Learning with Stochastic Reward Machines
PDFSparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks
PDFLearning Logic Programs Though Divide, Constrain, and Conquer
PDFImplicit Gradient Alignment in Distributed and Federated Learning
PDFHow Good Are Low-Rank Approximations in Gaussian Process Regression?
PDFKOALA: A Kalman Optimization Algorithm with Loss Adaptivity
PDFFirst-Order Convex Fitting and Its Application to Economics and Optimization
PDFGradient Temporal Difference with Momentum: Stability and Convergence
PDFDistillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes
PDFReducing Flipping Errors in Deep Neural Networks
PDFA Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits
PDFLocally Private k-Means Clustering with Constant Multiplicative Approximation and Near-Optimal Additive Error
PDFSafe Online Convex Optimization with Unknown Linear Safety Constraints
PDFDeconvolutional Density Network: Modeling Free-Form Conditional Distributions
PDFMultiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models
PDFSimultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model
PDFClustering Interval-Censored Time-Series for Disease Phenotyping
PDFEfficient Robust Training via Backward Smoothing
PDFAn Online Learning Approach to Sequential User-Centric Selection Problems
PDFBetter Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting
PDFMutual Nearest Neighbor Contrast and Hybrid Prototype Self-Training for Universal Domain Adaptation
PDFEvidential Neighborhood Contrastive Learning for Universal Domain Adaptation
PDFZero Stability Well Predicts Performance of Convolutional Neural Networks
PDFSemi-supervised Learning with Multi-Head Co-Training
PDFInstance Selection: A Bayesian Decision Theory Perspective
PDFInput-Specific Robustness Certification for Randomized Smoothing
PDFMultimodal Adversarially Learned Inference with Factorized Discriminators
PDFImbalance-Aware Uplift Modeling for Observational Data
PDFKAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-zero Training Loss
PDFBScNets: Block Simplicial Complex Neural Networks
PDFPrivate Rank Aggregation in Central and Local Models
PDFCombating Adversaries with Anti-adversaries
PDFDeformRS: Certifying Input Deformations with Randomized Smoothing
PDFLatent Time Neural Ordinary Differential Equations
PDFBeyond GNNs: An Efficient Architecture for Graph Problems
PDFProgrammatic Modeling and Generation of Real-Time Strategic Soccer Environments for Reinforcement Learning
PDFAdmissible Policy Teaching through Reward Design
PDFEntropy-Based Logic Explanations of Neural Networks
PDFTraining Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
PDFA Fast Algorithm for PAC Combinatorial Pure Exploration
PDFModeling Attrition in Recommender Systems with Departing Bandits
PDFFederated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better
PDFRobust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay
PDFErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions
PDFFeedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs
PDFBreaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows
PDFShrub Ensembles for Online Classification
PDFNoiseGrad — Enhancing Explanations by Introducing Stochasticity to Model Weights
PDFLeaping through Time with Gradient-Based Adaptation for Recommendation
PDFActive Sampling for Text Classification with Subinstance Level Queries
PDFContext-Specific Representation Abstraction for Deep Option Learning
PDFFisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition
PDFDistributed Learning with Strategic Users: A Repeated Game Approach
PDF