Papers
Mon 15 Feb 2021
169 papers
- Membership Inference Attacks are Easier on Difficult ProblemsLLM safety and security → Membership inference attacks
- Learning from Demonstrations using Signal Temporal LogicOffline RL and imitation learning from data → Robot learning from demonstration
- Saving Stochastic Bandits from Poisoning Attacks via Limited Data VerificationLLM safety and security → Backdoor and data poisoning attacks
- Improved Customer Transaction Classification using Semi-Supervised Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Surface Warping Incorporating Machine Learning Assisted Domain Likelihood Estimation: A New Paradigm in Mine Geology Modelling and Automation
- Within-Document Event Coreference with BERT-Based Contextualized Representations
- A Machine Learning Approach for Early Detection of Fish Diseases by Analyzing Water Quality
- HSR: Hyperbolic Social Recommender
- ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models
- A Knowledge-based Approach for the Automatic Construction of Skill Graphs for Online Monitoring
- Data Interpolation Accuracy Comparison: Gravity Model Versus Radial Basis Function
- Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport
- VA-RED2: Video Adaptive Redundancy Reduction
- PSA-Net: Deep Learning based Physician Style-Aware Segmentation Network for Post-Operative Prostate Cancer Clinical Target Volume
- A Hidden Challenge of Link Prediction: Which Pairs to Check?
- Momentum Residual Neural Networks
- GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
- Unified Shapley Framework to Explain Prediction Drift
- Low Curvature Activations Reduce Overfitting in Adversarial Training
- KNH: Multi-View Modeling with K-Nearest Hyperplanes Graph for Misinformation Detection
- Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
- Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
- Identifying Misinformation from Website Screenshots
- Self-Supervised Features Improve Open-World Learning
- Meta Back-translation
- Corneal Pachymetry by AS-OCT after Descemet's Membrane Endothelial Keratoplasty
- MARINA: Faster Non-Convex Distributed Learning with Compression
- "From What I see, this makes sense": Seeing meaning in algorithmic results
- How COVID-19 Is Changing Our Language : Detecting Semantic Shift in Twitter Word Embeddings
- Topological Graph Neural Networks
- One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes
- Deep Neural Networks for Radar Waveform Classification
- Controlling False Discovery Rates under Cross-Sectional Correlations
- KnowledgeCheckR: Intelligent Techniques for Counteracting Forgetting
- An Operator Theoretic Approach for Analyzing Sequence Neural Networks
- Anomalous Sound Detection with Machine Learning: A Systematic Review
- Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components
- Certified Robustness to Programmable Transformations in LSTMs
- What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
- Online hyperparameter optimization by real-time recurrent learning
- HDMI: High-order Deep Multiplex Infomax
- Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring
- Scaling Up Exact Neural Network Compression by ReLU Stability
- Efficient Learning with Arbitrary Covariate Shift
- Enhancing the Spatio-temporal Observability of Grid-Edge Resources in Distribution Grids
- Top-k eXtreme Contextual Bandits with Arm Hierarchy
- Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks
- Universal Adversarial Examples and Perturbations for Quantum Classifiers
- PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
- Online learning of Riemannian hidden Markov models in homogeneous Hadamard spaces
- Neural Posterior Regularization for Likelihood-Free Inference
- End-to-End Egospheric Spatial Memory
- How Convolutional Neural Networks Deal with Aliasing
- Learning Intra-Batch Connections for Deep Metric Learning
- Deep Co-Attention Network for Multi-View Subspace Learning
- A Data Quality-Driven View of MLOps
- Personalization Strategies for End-to-End Speech Recognition Systems
- Zero-Shot Self-Supervised Learning for MRI Reconstruction
- Network of Tensor Time Series
- Detection and severity classification of COVID-19 in CT images using deep learning
- Neural Network Compression for Noisy Storage Devices
- TI-Capsule: Capsule Network for Stock Exchange Prediction
- How RL Agents Behave When Their Actions Are Modified
- How to Learn when Data Reacts to Your Model: Performative Gradient Descent
- Scalable nonparametric Bayesian learning for heterogeneous and dynamic velocity fields
- Does the Adam Optimizer Exacerbate Catastrophic Forgetting?
- Fair and Optimal Cohort Selection for Linear Utilities
- A Gated Fusion Network for Dynamic Saliency Prediction
- Translational Equivariance in Kernelizable Attention
- Nonintrusive Uncertainty Quantification for automotive crash problems with VPS/Pamcrash
- Geometric feature performance under downsampling for EEG classification tasks
- A closer look at temporal variability in dynamic online learning
- Causal Markov Decision Processes: Learning Good Interventions Efficiently
- Overview of the TREC 2020 deep learning track
- Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems
- Consistency-based Merging of Variability Models
- A first look into the carbon footprint of federated learning
- RMS-Net: Regression and Masking for Soccer Event Spotting
- FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
- Learning image quality assessment by reinforcing task amenable data selection
- Goal-oriented adaptive sampling under random field modelling of response probability distributions
- Colored Kimia Path24 Dataset: Configurations and Benchmarks with Deep Embeddings
- A generalized quadratic loss for SVM and Deep Neural Networks
- UserReg: A Simple but Strong Model for Rating Prediction
- Seeing by haptic glance: reinforcement learning-based 3D object Recognition
- Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT
- A Reference Model for IoT Embodied Agents Controlled by Neural Networks
- On Riemannian Stochastic Approximation Schemes with Fixed Step-Size
- User Embedding based Neighborhood Aggregation Method for Inductive Recommendation
- Machine Learning Model Development from a Software Engineering Perspective: A Systematic Literature Review
- Transfer Learning for Future Wireless Networks: A Comprehensive Survey
- Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
- Certifiably Robust Variational Autoencoders
- Player-Centered AI for Automatic Game Personalization: Open Problems
- Data-driven Analysis for Understanding Team Sports Behaviors
- High-Dimensional Gaussian Process Inference with Derivatives
- WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
- Crowdsourcing Parallel Corpus for English-Oromo Neural Machine Translation using Community Engagement Platform
- CHARET: Character-centered Approach to Emotion Tracking in Stories
- The corruptive force of AI-generated advice
All 169
- Scalable Vector Gaussian Information Bottleneck
- Cooperation and Reputation Dynamics with Reinforcement Learning
- Distributed Online Learning for Joint Regret with Communication Constraints
- Short- and long-term prediction of a chaotic flow: A physics-constrained reservoir computing approach
- GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent
- Plug-and-Play gradient-based denoisers applied to CT image enhancement
- CLNet: Complex Input Lightweight Neural Network designed for Massive MIMO CSI Feedback
- One-shot learning for the long term: consolidation with an artificial hippocampal algorithm
- Annealed Flow Transport Monte Carlo
- On the Impact of Device and Behavioral Heterogeneity in Federated Learning
- ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learning
- DOBF: A Deobfuscation Pre-Training Objective for Programming Languages
- Spatio-temporal Graph-RNN for Point Cloud Prediction
- Holographic Cell Stiffness Mapping Using Acoustic Stimulation
- Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
- DAC: Deep Autoencoder-based Clustering, a General Deep Learning Framework of Representation Learning
- Neuro-algorithmic Policies enable Fast Combinatorial Generalization
- Video Analytics on IoT devices
- Federated Dropout Learning for Hybrid Beamforming With Spatial Path Index Modulation In Multi-User mmWave-MIMO Systems
- OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving
- FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation
- Data Quality Matters For Adversarial Training: An Empirical Study
- Approximation to Object Conditional Validity with Inductive Conformal Predictors
- Fast and accurate optimization on the orthogonal manifold without retraction
- DiffCo: Auto-Differentiable Proxy Collision Detection with Multi-class Labels for Safety-Aware Trajectory Optimization
- Jira: a Kurdish Speech Recognition System Designing and Building Speech Corpus and Pronunciation Lexicon
- Tractable structured natural gradient descent using local parameterizations
- Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games
- Information flows of diverse autoencoders
- Beyond the English Web: Zero-Shot Cross-Lingual and Lightweight Monolingual Classification of Registers
- And/or trade-off in artificial neurons: impact on adversarial robustness
- Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization
- MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training
- On the Inherent Regularization Effects of Noise Injection During Training
- Generation For Adaption: A GAN-Based Approach for 3D Domain Adaption with Point Cloud Data
- REST: Relational Event-driven Stock Trend Forecasting
- Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification
- A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum
- A Unified Batch Selection Policy for Active Metric Learning
- Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
- Generating Structured Adversarial Attacks Using Frank-Wolfe Method
- Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learning
- Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator
- Win-Fail Action Recognition
- QuickBrowser: A Unified Model to Detect and Read Simple Object in Real-time
- Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
- MATCH: Metadata-Aware Text Classification in A Large Hierarchy
- On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers
- Developing parsimonious ensembles using predictor diversity within a reinforcement learning framework
- Capturing Detailed Deformations of Moving Human Bodies
- OntoZSL: Ontology-enhanced Zero-shot Learning
- Machine Learning on Camera Images for Fast mmWave Beamforming
- Relaxation of optimal transport problem via strictly convex functions
- AI Ethics Needs Good Data
- Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs
- Guided Interpolation for Adversarial Training
- Cross-modal Adversarial Reprogramming
- A Global to Local Double Embedding Method for Multi-person Pose Estimation
- The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball Methods
- Confidence-Aware Learning Assistant
- I-vector Based Within Speaker Voice Quality Identification on connected speech
- Vehicle to Vehicle (V2V) Communication Protocol: Components, Benefits, Challenges, Safety and Machine Learning Applications
- CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification
- Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
- A Deep Adversarial Model for Suffix and Remaining Time Prediction of Event Sequences
- Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series
- Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows
- 3D Fully Convolutional Neural Networks with Intersection Over Union Loss for Crop Mapping from Multi-Temporal Satellite Images
- Anomaly Detection for Scenario-based Insider Activities using CGAN Augmented Data