Papers
Fri 12 Feb 2021
145 papers
- Learning Student-Friendly Teacher Networks for Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Scalable Bayesian Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- Self-Supervised Multisensor Change Detection
- Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks
- Multimodal Punctuation Prediction with Contextual Dropout
- InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model
- A bi-level encoding scheme for the clustered shortest-path tree problem in multifactorial optimization
- Towards AIOps in Edge Computing Environments
- Comparative Code Structure Analysis using Deep Learning for Performance Prediction
- Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
- AI Uncertainty Based on Rademacher Complexity and Shannon Entropy
- Demystifying Inductive Biases for β-VAE Based Architectures
- Characterizing English Variation across Social Media Communities with BERT
- Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR
- Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits
- Understanding self-supervised Learning Dynamics without Contrastive Pairs
- Planning and Learning Using Adaptive Entropy Tree Search
- Parameter-free Locally Accelerated Conditional Gradients
- Blind stain separation using model-aware generative learning and its applications on fluorescence microscopy images
- Reinforcement Learning For Data Poisoning on Graph Neural Networks
- Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
- A Unified Lottery Ticket Hypothesis for Graph Neural Networks
- They, Them, Theirs: Rewriting with Gender-Neutral English
- Q-Value Weighted Regression: Reinforcement Learning with Limited Data
- Machine Learning for Mechanical Ventilation Control
- INSTA-YOLO: Real-Time Instance Segmentation
- Generalizing Decision Making for Automated Driving with an Invariant Environment Representation using Deep Reinforcement Learning
- Technical Challenges for Training Fair Neural Networks
- Supporting search engines with knowledge and context
- MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset
- Stochastic Gradient Langevin Dynamics with Variance Reduction
- On automatic extraction of on-street parking spaces using park-out events data
- Multimodal Data Visualization and Denoising with Integrated Diffusion
- A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization
- Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding
- Structural Information Preserving for Graph-to-Text Generation
- Realizable Universal Adversarial Perturbations for Malware
- Hybrid phonetic-neural model for correction in speech recognition systems
- Edge Minimizing the Student Conflict Graph
- Discovery of Options via Meta-Learned Subgoals
- Appearance of Random Matrix Theory in Deep Learning
- Kronecker-factored Quasi-Newton Methods for Deep Learning
- Learning Deep Neural Networks under Agnostic Corrupted Supervision
- A novel method for object detection using deep learning and CAD models
- Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives
- Proximal and Federated Random Reshuffling
- Explaining Neural Scaling Laws
- On the Paradox of Certified Training
- Matching Point Sets with Quantum Circuit Learning
- Efficient Conditional GAN Transfer with Knowledge Propagation across Classes
- Bias-Free Scalable Gaussian Processes via Randomized Truncations
- Rethinking Eye-blink: Assessing Task Difficulty through Physiological Representation of Spontaneous Blinking
- Destination similarity based on implicit user interest
- DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
- Adversarial Branch Architecture Search for Unsupervised Domain Adaptation
- A model for traffic incident prediction using emergency braking data
- Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction
- End-to-end Audio-visual Speech Recognition with Conformers
- Robust White Matter Hyperintensity Segmentation on Unseen Domain
- A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Models
- Bayesian Quadrature on Riemannian Data Manifolds
- ReLU Neural Networks of Polynomial Size for Exact Maximum Flow Computation
- An Overview of Recommender Systems and Machine Learning in Feature Modeling and Configuration
- Deep Reinforcement Learning for Backup Strategies against Adversaries
- Do-calculus enables estimation of causal effects in partially observed biomolecular pathways
- A Generative Model for Hallucinating Diverse Versions of Super Resolution Images
- MetaGrad: Adaptation using Multiple Learning Rates in Online Learning
- Optimizing Inference Performance of Transformers on CPUs
- Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders
- Intelligent Software Web Agents: A Gap Analysis
- Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
- Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks
- Semantically-Conditioned Negative Samples for Efficient Contrastive Learning
- Modeling Dynamic User Interests: A Neural Matrix Factorization Approach
- Neural Architecture Search as Program Transformation Exploration
- Pareto Optimal Model Selection in Linear Bandits
- Outdoor inverse rendering from a single image using multiview self-supervision
- Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability
- Disturbing Reinforcement Learning Agents with Corrupted Rewards
- A Computability Perspective on (Verified) Machine Learning
- Reviving Iterative Training with Mask Guidance for Interactive Segmentation
- Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders
- Shrinkage Bayesian Causal Forests for Heterogeneous Treatment Effects Estimation
- Bayesian Neural Network Priors Revisited
- Analysis of Interpolation based Image In-painting Approaches
- How Far Should We Look Back to Achieve Effective Real-Time Time-Series Anomaly Detection?
- Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations
- Continuous Learning in Neural Machine Translation using Bilingual Dictionaries
- Online Graph Dictionary Learning
- Exploiting Spline Models for the Training of Fully Connected Layers in Neural Network
- A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages
- Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
- Two Training Strategies for Improving Relation Extraction over Universal Graph
- Jacobian Determinant of Normalizing Flows
- Improving Object Detection in Art Images Using Only Style Transfer
- Sequential Neural Posterior and Likelihood Approximation
- Robust and integrative Bayesian neural networks for likelihood-free parameter inference
- VitrAI -- Applying Explainable AI in the Real World
- Large-Scale Representation Learning on Graphs via Bootstrapping
- A Non-Intrusive Machine Learning Solution for Malware Detection and Data Theft Classification in Smartphones
All 145
- Interpretable Predictive Maintenance for Hard Drives
- Predicting and Attending to Damaging Collisions for Placing Everyday Objects in Photo-Realistic Simulations
- Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization
- End-to-End Intelligent Framework for Rockfall Detection
- Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
- Adaptive Sampling for Fast Constrained Maximization of Submodular Function
- Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective
- HNPE: Leveraging Global Parameters for Neural Posterior Estimation
- Transformer Language Models with LSTM-based Cross-utterance Information Representation
- Content-Aware Speaker Embeddings for Speaker Diarisation
- Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
- Deep Sound Field Reconstruction in Real Rooms: Introducing the ISOBEL Sound Field Dataset
- Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier
- The MSR-Video to Text Dataset with Clean Annotations
- Data Analytics and Machine Learning Methods, Techniques and Tool for Model-Driven Engineering of Smart IoT Services
- Broad-UNet: Multi-scale feature learning for nowcasting tasks
- VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention
- Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia
- Emoji-Based Transfer Learning for Sentiment Tasks
- Explaining predictive models using Shapley values and non-parametric vine copulas
- Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors
- Densely Deformable Efficient Salient Object Detection Network
- A Too-Good-to-be-True Prior to Reduce Shortcut Reliance
- Multiversal views on language models
- Uncertainty-Aware Semi-Supervised Method Using Large Unlabeled and Limited Labeled COVID-19 Data
- The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
- Multi-source Pseudo-label Learning of Semantic Segmentation for the Scene Recognition of Agricultural Mobile Robots
- The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
- Neural Inverse Text Normalization
- Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks
- Confounding Tradeoffs for Neural Network Quantization
- Dynamic Precision Analog Computing for Neural Networks
- A Decentralized Approach towards Responsible AI in Social Ecosystems
- SCOUT: Socially-COnsistent and UndersTandable Graph Attention Network for Trajectory Prediction of Vehicles and VRUs
- Min-Max-Plus Neural Networks
- Contrastive Unsupervised Learning for Speech Emotion Recognition
- A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes
- Projected Wasserstein gradient descent for high-dimensional Bayesian inference
- Physics-Informed Graphical Neural Network for Parameter & State Estimations in Power Systems
- Personalized Visualization Recommendation
- Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices
- Efficient Algorithms for Federated Saddle Point Optimization
- Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients
- ReRankMatch: Semi-Supervised Learning with Semantics-Oriented Similarity Representation
- On Automatic Parsing of Log Records