Papers
Tue 16 Feb 2021
182 papers
- COMBO: Conservative Offline Model-Based Policy OptimizationOffline RL and imitation learning from data → Offline RL algorithms
- Adversarial Targeted Forgetting in Regularization and Generative Based Continual Learning ModelsLLM safety and security → Backdoor and data poisoning attacks
- Learning curves of generic features maps for realistic datasets with a teacher-student modelKnowledge distillation → General knowledge distillation methods
- Inverse Reinforcement Learning in a Continuous State Space with Formal GuaranteesOffline RL and imitation learning from data → Inverse reinforcement learning
- Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge DistillationKnowledge distillation → Speech and audio distillation
- TradeR: Practical Deep Hierarchical Reinforcement Learning for Trade Execution
- New Methods for Detecting Concentric Objects With High Accuracy
- Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release
- Moral Decision-Making in Medical Hybrid Intelligent Systems: A Team Design Patterns Approach to the Bias Mitigation and Data Sharing Design Problems
- Investigating Underlying Drivers of Variability in Residential Energy Usage Patterns with Daily Load Shape Clustering of Smart Meter Data
- A Qualitative Theory of Cognitive Attitudes and their Change
- Predicting Material Properties Using a 3D Graph Neural Network with Invariant Local Descriptors
- Convergence of stochastic gradient descent schemes for Lojasiewicz-landscapes
- Recommending Training Set Sizes for Classification
- Comparing and Combining Approximate Computing Frameworks
- A Regret Analysis of Bilateral Trade
- Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications
- DEUP: Direct Epistemic Uncertainty Prediction
- Pattern Sampling for Shapelet-based Time Series Classification
- Shape-Tailored Deep Neural Networks
- Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
- Finding the Ground-Truth from Multiple Labellers: Why Parameters of the Task Matter
- Adversarially Robust Kernel Smoothing
- COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
- Deep Neural Network Based Differential Equation Solver for HIV Enzyme Kinetics
- Robust Factorization of Real-world Tensor Streams with Patterns, Missing Values, and Outliers
- Prioritizing Original News on Facebook
- A Review of Testing Object-Based Environment Perception for Safe Automated Driving
- Lexicographically Fair Learning: Algorithms and Generalization
- Towards the Right Kind of Fairness in AI
- Globally-Robust Neural Networks
- Selfie Periocular Verification using an Efficient Super-Resolution Approach
- Smoothed Analysis with Adaptive Adversaries
- TableLab: An Interactive Table Extraction System with Adaptive Deep Learning
- Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine
- Scaling Neuroscience Research using Federated Learning
- Complex Momentum for Optimization in Games
- Multi-Stage Transmission Line Flow Control Using Centralized and Decentralized Reinforcement Learning Agents
- Evaluating Multi-label Classifiers with Noisy Labels
- Searching for Search Errors in Neural Morphological Inflection
- Learning deep multiresolution representations for pansharpening
- Improving Visual Place Recognition Performance by Maximising Complementarity
- Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
- Darknet Traffic Big-Data Analysis and Network Management to Real-Time Automating the Malicious Intent Detection Process by a Weight Agnostic Neural Networks Framework
- Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
- Topological Obstructions to Autoencoding
- IntSGD: Adaptive Floatless Compression of Stochastic Gradients
- Analysis of feature learning in weight-tied autoencoders via the mean field lens
- Quantifying the effects of environment and population diversity in multi-agent reinforcement learning
- CTAB-GAN: Effective Table Data Synthesizing
- Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations
- Boosting Low-Resource Biomedical QA via Entity-Aware Masking Strategies
- Efficient Competitions and Online Learning with Strategic Forecasters
- Revisiting Language Encoding in Learning Multilingual Representations
- Topological Deep Learning: Classification Neural Networks
- Stochastic Variance Reduction for Variational Inequality Methods
- Learning Symbolic Expressions: Mixed-Integer Formulations, Cuts, and Heuristics
- NoiseQA: Challenge Set Evaluation for User-Centric Question Answering
- Learning Invariant Representations using Inverse Contrastive Loss
- Faster Kernel Matrix Algebra via Density Estimation
- An Information-Theoretic Justification for Model Pruning
- Context-Aware Prosody Correction for Text-Based Speech Editing
- Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity
- A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles
- Instance Localization for Self-supervised Detection Pretraining
- Resource allocation in dynamic multiagent systems
- Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients
- On Mathews Correlation Coefficient and Improved Distance Map Loss for Automatic Glacier Calving Front Segmentation in SAR Imagery
- Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation
- Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary
- Dynamic neighbourhood optimisation for task allocation using multi-agent
- Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models
- A Federated Data-Driven Evolutionary Algorithm
- Evaluating Node Embeddings of Complex Networks
- An Effort to Measure Customer Relationship Performance in Indonesia's Fintech Industry
- Dataset Condensation with Differentiable Siamese Augmentation
- Hierarchical VAEs Know What They Don't Know
- Classification of multivariate weakly-labelled time-series with attention
- Differentially Private Quantiles
- Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models
- The MELODIC family for simultaneous binary logistic regression in a reduced space
- Non-Autoregressive Text Generation with Pre-trained Language Models
- Unifying Lower Bounds on Prediction Dimension of Consistent Convex Surrogates
- The Yin-Yang dataset
- Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression
- Improper Reinforcement Learning with Gradient-based Policy Optimization
- Automated Identification of Vulnerable Devices in Networks using Traffic Data and Deep Learning
- Constructing Multiclass Classifiers using Binary Classifiers Under Log-Loss
- Comparison of semi-supervised deep learning algorithms for audio classification
- Value of Information for Argumentation based Intelligence Analysis
- Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination
- Just Noticeable Difference for Deep Machine Vision
- Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
- Integrating Floor Plans into Hedonic Models for Rent Price Appraisal
- RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
- End-to-End Automatic Speech Recognition with Deep Mutual Learning
- Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents
- Nominal Unification and Matching of Higher Order Expressions with Recursive Let
- Hough2Map -- Iterative Event-based Hough Transform for High-Speed Railway Mapping
- IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learning
All 182
- Spatio-Temporal Multi-step Prediction of Influenza Outbreaks
- Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks
- Dynamic Virtual Graph Significance Networks for Predicting Influenza
- Meta-Path-Free Representation Learning on Heterogeneous Networks
- Trees-Based Models for Correlated Data
- Recommender Systems for Configuration Knowledge Engineering
- Multivariable Fractional Polynomials for lithium-ion batteries degradation models under dynamic conditions
- Message Passing Descent for Efficient Machine Learning
- Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks
- EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search
- GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
- Supervised Training of Dense Object Nets using Optimal Descriptors for Industrial Robotic Applications
- Composing Pick-and-Place Tasks By Grounding Language
- A Law of Robustness for Weight-bounded Neural Networks
- An AutoML-based Approach to Multimodal Image Sentiment Analysis
- Making the most of your day: online learning for optimal allocation of time
- Boosting Deep Transfer Learning for COVID-19 Classification
- Orthogonal Features-based EEG Signal Denoising using Fractionally Compressed AutoEncoder
- Learning the Noise of Failure: Intelligent System Tests for Robots
- Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbation
- Restore from Restored: Single-image Inpainting
- Axial Residual Networks for CycleGAN-based Voice Conversion
- Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining
- Steadily Learn to Drive with Virtual Memory
- A comparative study on movement feature in different directions for micro-expression recognition
- Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries
- On the use of generative deep neural networks to synthesize artificial multichannel EEG signals
- Zero-Shot Adaptation for mmWave Beam-Tracking on Overhead Messenger Wires through Robust Adversarial Reinforcement Learning
- A Multiscale Graph Convolutional Network for Change Detection in Homogeneous and Heterogeneous Remote Sensing Images
- Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet
- Design a Technology Based on the Fusion of Genetic Algorithm, Neural network and Fuzzy logic
- Transferring Domain Knowledge with an Adviser in Continuous Tasks
- EDITH :ECG biometrics aided by Deep learning for reliable Individual auTHentication
- Joint self-supervised blind denoising and noise estimation
- Uncertainty-based method for improving poorly labeled segmentation datasets
- Concentration of measure and generalized product of random vectors with an application to Hanson-Wright-like inequalities
- A Thorough View of Exact Inference in Graphs from the Degree-4 Sum-of-Squares Hierarchy
- Improving speech recognition models with small samples for air traffic control systems
- Representing Hierarchical Structure by Using Cone Embedding
- Temporal-Amount Snapshot MultiGraph for Ethereum Transaction Tracking
- Training Stacked Denoising Autoencoders for Representation Learning
- EfficientLPS: Efficient LiDAR Panoptic Segmentation
- TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
- A Mental Trespass? Unveiling Truth, Exposing Thoughts and Threatening Civil Liberties with Non-Invasive AI Lie Detection
- DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
- A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
- D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis
- LEAD: LiDAR Extender for Autonomous Driving
- TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
- The Elliptical Potential Lemma for General Distributions with an Application to Linear Thompson Sampling
- FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary
- SiMaN: Sign-to-Magnitude Network Binarization
- A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection
- A General Descent Aggregation Framework for Gradient-based Bi-level Optimization
- Twin Augmented Architectures for Robust Classification of COVID-19 Chest X-Ray Images
- Follow-the-Regularized-Leader Routes to Chaos in Routing Games
- A Sub-band Approach to Deep Denoising Wavelet Networks and a Frequency-adaptive Loss for Perceptual Quality
- Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach
- Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation
- Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey
- Multi-Attribute Enhancement Network for Person Search
- A Combination of Multi-Objective Genetic Algorithm and Deep Learning for Music Harmony Generation
- Efficient Discretizations of Optimal Transport
- AlphaNet: Improved Training of Supernets with Alpha-Divergence
- A Survey of Machine Learning for Computer Architecture and Systems
- ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks
- Local Hyper-Flow Diffusion
- Deep Equilibrium Architectures for Inverse Problems in Imaging
- Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view
- DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
- GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software
- Near-Optimal Algorithms for Differentially Private Online Learning in a Stochastic Environment
- Structured Dropout Variational Inference for Bayesian Neural Networks
- Have Attention Heads in BERT Learned Constituency Grammar?
- Focal Inverse Distance Transform Maps for Crowd Localization
- Training Larger Networks for Deep Reinforcement Learning
- User-Inspired Posterior Network for Recommendation Reason Generation
- Information Ranking Using Optimum-Path Forest
- Few-Shot Graph Learning for Molecular Property Prediction
- MITNet: GAN Enhanced Magnetic Induction Tomography Based on Complex CNN
- Engineering Education in the Age of Autonomous Machines
- A Deep-Learning Approach For Direct Whole-Heart Mesh Reconstruction