Papers
Tue 26 Oct 2021
217 papers
- The Difficulty of Passive Learning in Deep Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Towards Hyperparameter-free Policy Selection for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Learning Robust Controllers Via Probabilistic Model-Based Policy SearchWorld models → Latent dynamics models and model-based RL
- Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial OutcomesLLM safety and security → Machine unlearning
- Response-based Distillation for Incremental Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Towards More Generalizable One-shot Visual Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity
- Neural Program Generation Modulo Static Analysis
- Fragment-based Sequential Translation for Molecular Optimization
- Combining expert knowledge and neural networks to model environmental stresses in agriculture
- Adaptive Modeling Powers Fast Multi-parameter Fitting of CARS Spectra
- A Frequency Perspective of Adversarial Robustness
- Multi-Agent Advisor Q-Learning
- Fuzzy Conceptual Graphs: a comparative discussion
- CLAUSEREC: A Clause Recommendation Framework for AI-aided Contract Authoring
- CAFE: Catastrophic Data Leakage in Vertical Federated Learning
- cgSpan: Pattern Mining in Conceptual Graphs
- Mapping conditional distributions for domain adaptation under generalized target shift
- Brain-inspired feature exaggeration in generative replay for continual learning
- Adversarial Robustness in Multi-Task Learning: Promises and Illusions
- Ensemble Federated Adversarial Training with Non-IID data
- Stable Anderson Acceleration for Deep Learning
- SE(3) Equivariant Graph Neural Networks with Complete Local Frames
- Adversarial Online Learning with Variable Plays in the Pursuit-Evasion Game: Theoretical Foundations and Application in Connected and Automated Vehicle Cybersecurity
- CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration
- Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee
- Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
- Towards Model Reduction for Power System Transients with Physics-Informed PDE
- Meta-learning with an Adaptive Task Scheduler
- How to transfer algorithmic reasoning knowledge to learn new algorithms?
- Polynomial-Spline Neural Networks with Exact Integrals
- NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
- A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
- Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning
- Conflict-Averse Gradient Descent for Multi-task Learning
- iALS++: Speeding up Matrix Factorization with Subspace Optimization
- Robustness of Graph Neural Networks at Scale
- Revisiting the Performance of iALS on Item Recommendation Benchmarks
- MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
- Surrogate Regret Bounds for Polyhedral Losses
- Improving Local Effectiveness for Global robust training
- Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection
- Deep Integrated Pipeline of Segmentation Guided Classification of Breast Cancer from Ultrasound Images
- Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
- Cluster-and-Conquer: A Framework For Time-Series Forecasting
- MisConv: Convolutional Neural Networks for Missing Data
- TOD: GPU-accelerated Outlier Detection via Tensor Operations
- CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator
- SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data
- Efficient Learning and Decoding of the Continuous-Time Hidden Markov Model for Disease Progression Modeling
- Controllable Data Augmentation Through Deep Relighting
- Leveraging Local Temporal Information for Multimodal Scene Classification
- Revisiting Batch Norm Initialization
- Learning Collaborative Policies to Solve NP-hard Routing Problems
- Fair Sequential Selection Using Supervised Learning Models
- Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers
- CHIP: CHannel Independence-based Pruning for Compact Neural Networks
- Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions
- The Value of Information When Deciding What to Learn
- Video-based fully automatic assessment of open surgery suturing skills
- Diachronic Text Mining Investigation of Therapeutic Candidates for COVID-19
- Rademacher Random Projections with Tensor Networks
- Nonparametric Matrix Estimation with One-Sided Covariates
- On the Effects of Artificial Data Modification
- Unbiased Graph Embedding with Biased Graph Observations
- On sensitivity of meta-learning to support data
- Can't Fool Me: Adversarially Robust Transformer for Video Understanding
- Boosted CVaR Classification
- Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
- Rapid IoT Device Identification at the Edge
- CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation
- Provably Robust Model-Centric Explanations for Critical Decision-Making
- Frequency Centric Defense Mechanisms against Adversarial Examples
- Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias
- NeRV: Neural Representations for Videos
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- HR-RCNN: Hierarchical Relational Reasoning for Object Detection
- Dynamic Causal Bayesian Optimization
- Heterogeneous Temporal Graph Neural Network
- Understanding Interlocking Dynamics of Cooperative Rationalization
- Deep Explicit Duration Switching Models for Time Series
- Assessing Evaluation Metrics for Speech-to-Speech Translation
- Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs
- FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective
- Defensive Tensorization
- Average-Reward Learning and Planning with Options
- Interpretable Decision Trees Through MaxSAT
- A Light-weight Interpretable Compositional Model for Nuclei Detection and Weakly-Supervised Segmentation
- Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization
- Real-time division-of-focal-plane polarization imaging system with progressive networks
- CloudFindr: A Deep Learning Cloud Artifact Masker for Satellite DEM Data
- Driving Style Recognition Using Interval Type-2 Fuzzy Inference System and Multiple Experts Decision Making
- Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective
- Deeper-GXX: Deepening Arbitrary GNNs
- Post-processing for Individual Fairness
- Pyramidal Blur Aware X-Corner Chessboard Detector
- Diversity and Generalization in Neural Network Ensembles
- Data-Driven Time Series Reconstruction for Modern Power Systems Research
- AugMax: Adversarial Composition of Random Augmentations for Robust Training
- Interpretable Identification of Comorbidities Associated with Recurrent ED and Inpatient Visits
All 217
- DPCOVID: Privacy-Preserving Federated Covid-19 Detection
- Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD
- Topologically penalized regression on manifolds
- SpectroscopyNet: Learning to pre-process Spectroscopy Signals without clean data
- H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion
- PARIS: Personalized Activity Recommendation for Improving Sleep Quality
- Robust Multi-view Registration of Point Sets with Laplacian Mixture Model
- Disrupting Deep Uncertainty Estimation Without Harming Accuracy
- DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples
- Improving the efficacy of Deep Learning models for Heart Beat detection on heterogeneous datasets
- Geometric Transformer for End-to-End Molecule Properties Prediction
- Deep DIC: Deep Learning-Based Digital Image Correlation for End-to-End Displacement and Strain Measurement
- Semi-supervised dry herbage mass estimation using automatic data and synthetic images
- HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information
- ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
- YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs
- Hierarchical Transformers Are More Efficient Language Models
- DASentimental: Detecting depression, anxiety and stress in texts via emotional recall, cognitive networks and machine learning
- TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition
- Causal Effect Estimation using Variational Information Bottleneck
- Addressing out-of-distribution label noise in webly-labelled data
- A Fast Horizon Detector and a New Annotated Dataset for Maritime Video Processing
- Annotating Implicit Reasoning in Arguments with Causal Links
- An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling
- A Closer Look at Reference Learning for Fourier Phase Retrieval
- BioIE: Biomedical Information Extraction with Multi-head Attention Enhanced Graph Convolutional Network
- Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN
- A Personalized Diagnostic Generation Framework Based on Multi-source Heterogeneous Data
- Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
- C2SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
- W-Net: A Two-Stage Convolutional Network for Nucleus Detection in Histopathology Image
- Bootstrapping Concept Formation in Small Neural Networks
- Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
- A Precision Diagnostic Framework of Renal Cell Carcinoma on Whole-Slide Images using Deep Learning
- s2s-ft: Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning
- EDLaaS: Fully Homomorphic Encryption Over Neural Network Graphs for Vision and Private Strawberry Yield Forecasting
- Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning
- Incremental Learning for Animal Pose Estimation using RBF k-DPP
- TME-BNA: Temporal Motif-Preserving Network Embedding with Bicomponent Neighbor Aggregation
- Arbitrary Distribution Modeling with Censorship in Real-Time Bidding Advertising
- Concepts for Automated Machine Learning in Smart Grid Applications
- Real-time Human Response Prediction Using a Non-intrusive Data-driven Model Reduction Scheme
- Gradient representations in ReLU networks as similarity functions
- Distributional Reinforcement Learning for Multi-Dimensional Reward Functions
- Open Rule Induction
- Automated Support for Unit Test Generation: A Tutorial Book Chapter
- Periodic Activation Functions Induce Stationarity
- Emotion recognition in talking-face videos using persistent entropy and neural networks
- Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition
- Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks
- Non-Gaussian Gaussian Processes for Few-Shot Regression
- Cross-Region Building Counting in Satellite Imagery using Counting Consistency
- Directional Self-supervised Learning for Heavy Image Augmentations
- Single Morphing Attack Detection using Feature Selection and Visualisation based on Mutual Information
- Coherent False Seizure Prediction in Epilepsy, Coincidence or Providence?
- Online Variational Filtering and Parameter Learning
- An extended physics informed neural network for preliminary analysis of parametric optimal control problems
- Automating Control of Overestimation Bias for Reinforcement Learning
- Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
- Machine learning spectral functions in lattice QCD
- Modular Gaussian Processes for Transfer Learning
- AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification
- Accelerating Distributed Deep Reinforcement Learning by In-Network Experience Sampling
- Part & Whole Extraction: Towards A Deep Understanding of Quantitative Facts for Percentages in Text
- Shared Independent Component Analysis for Multi-Subject Neuroimaging
- Tensor Network Kalman Filtering for Large-Scale LS-SVMs
- Assessing the Sufficiency of Arguments through Conclusion Generation
- Meta-Learning for Multi-Label Few-Shot Classification
- TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining
- Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey
- Simultaneous Neural Machine Translation with Constituent Label Prediction
- Zero-Shot Action Recognition from Diverse Object-Scene Compositions
- Vector-valued Distance and Gyrocalculus on the Space of Symmetric Positive Definite Matrices
- CTRN: Class-Temporal Relational Network for Action Detection
- Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable
- Subject Adaptive EEG-based Visual Recognition
- CS-Rep: Making Speaker Verification Networks Embracing Re-parameterization
- MarS-FL: Enabling Competitors to Collaborate in Federated Learning
- On the Optimization Landscape of Maximum Mean Discrepancy
- Distributed Multi-Agent Deep Reinforcement Learning Framework for Whole-building HVAC Control
- A time-weighted metric for sets of trajectories to assess multi-object tracking algorithms
- A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures
- Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task
- AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain
- Deep Learning-based Segmentation of Cerebral Aneurysms in 3D TOF-MRA using Coarse-to-Fine Framework
- Contextual Similarity Aggregation with Self-attention for Visual Re-ranking
- Image Magnification Network for Vessel Segmentation in OCTA Images
- Phish-Defence: Phishing Detection Using Deep Recurrent Neural Networks
- Relay Variational Inference: A Method for Accelerated Encoderless VI
- Semantic Host-free Trojan Attack
- Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features
- TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation
- Task-Aware Meta Learning-based Siamese Neural Network for Classifying Obfuscated Malware
- Learning Rich Features for Gait Recognition by Integrating Skeletons and Silhouettes
- Revisiting randomized choices in isolation forests
- Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays
- Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
- Transferring Domain-Agnostic Knowledge in Video Question Answering
- A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
- Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design
- Self-Denoising Neural Networks for Few Shot Learning
- IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition
- ViDA-MAN: Visual Dialog with Digital Humans
- Instant Response Few-shot Object Detection with Meta Strategy and Explicit Localization Inference
- Task-Specific Dependency-based Word Embedding Methods
- EnTRPO: Trust Region Policy Optimization Method with Entropy Regularization
- Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set
- An Automatic Detection Method Of Cerebral Aneurysms In Time-Of-Flight Magnetic Resonance Angiography Images Based On Attention 3D U-Net
- Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations
- Exponential Graph is Provably Efficient for Decentralized Deep Training
- RGB Camera-based Physiological Sensing: Challenges and Future Directions
- A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEs
- Sinusoidal Flow: A Fast Invertible Autoregressive Flow
- How Should AI Interpret Rules? A Defense of Minimally Defeasible Interpretive Argumentation
- Decentralized Multi-Target Cross-Domain Recommendation for Multi-Organization Collaborations
- Robust Ellipsoid-specific Fitting via Expectation Maximization
- Recipes for when Physics Fails: Recovering Robust Learning of Physics Informed Neural Networks