Papers
Wed 27 Oct 2021
220 papers
- Mosaicking to Distill: Knowledge Distillation from Out-of-Domain DataKnowledge distillation → General knowledge distillation methods
- TRAIL: Near-Optimal Imitation Learning with Suboptimal DataOffline RL and imitation learning from data → Imitation learning methods
- Confidence-Aware Imitation Learning from Demonstrations with Varying OptimalityOffline RL and imitation learning from data → Imitation learning methods
- DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical RepresentationsWorld models → Latent dynamics models and model-based RL
- Learning from demonstrations with SACR2: Soft Actor-Critic with Reward RelabelingOffline RL and imitation learning from data → Imitation learning methods
- Transfer learning with causal counterfactual reasoning in Decision TransformersOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Beyond Classification: Knowledge Distillation using Multi-Object ImpressionsKnowledge distillation → Detection and dense prediction distillation
- Temporal Knowledge Distillation for On-device Audio ClassificationKnowledge distillation → Speech and audio distillation
- Object-Aware Regularization for Addressing Causal Confusion in Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Influential Papers in Artificial Intelligence and Paediatrics: Assessing RPYS by Experts Review
- Parameterized Explanations for Investor / Company Matching
- A multi-task learning-based optimization approach for finding diverse sets of material microstructures with desired properties and its application to texture optimization
- MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition
- Discovering Non-monotonic Autoregressive Orderings with Variational Inference
- LSTM-RPA: A Simple but Effective Long Sequence Prediction Algorithm for Music Popularity Prediction
- Towards Intelligent Load Balancing in Data Centers
- Self-supervised EEG Representation Learning for Automatic Sleep Staging
- A Novel Sleep Stage Classification Using CNN Generated by an Efficient Neural Architecture Search with a New Data Processing Trick
- Finite Horizon Q-learning: Stability, Convergence, Simulations and an application on Smart Grids
- A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning
- Nearest neighbor empirical processes
- Validating Gaussian Process Models with Simulation-Based Calibration
- The chemical space of terpenes: insights from data science and AI
- Telling Creative Stories Using Generative Visual Aids
- Towards a Taxonomy of Graph Learning Datasets
- L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization
- Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning
- Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers
- You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism
- Convolutional Deep Exponential Families
- Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection
- MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
- Masked LARk: Masked Learning, Aggregation and Reporting worKflow
- Warped Dynamic Linear Models for Time Series of Counts
- SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata
- When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer
- Combining Vagueness Detection with Deep Learning to Identify Fake News
- Spectrahedral Regression
- BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation
- SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation
- ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets
- Detecting Dementia from Speech and Transcripts using Transformers
- Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond
- Algorithmic encoding of protected characteristics in image-based models for disease detection
- Subtleties in the trainability of quantum machine learning models
- Dynamic Review-based Recommenders
- Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins
- Efficient Placard Discovery for Semantic Mapping During Frontier Exploration
- Generalized Shape Metrics on Neural Representations
- Towards Evaluating the Robustness of Neural Networks Learned by Transduction
- Vision Transformer for Classification of Breast Ultrasound Images
- Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection
- Lung Cancer Lesion Detection in Histopathology Images Using Graph-Based Sparse PCA Network
- Designing Machine Learning Surrogates using Outputs of Molecular Dynamics Simulations as Soft Labels
- A Survey of Self-Supervised and Few-Shot Object Detection
- Sharp-GAN: Sharpness Loss Regularized GAN for Histopathology Image Synthesis
- Identifiable Generative Models for Missing Not at Random Data Imputation
- Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
- Alternating Learning Approach for Variational Networks and Undersampling Pattern in Parallel MRI Applications
- Towards Realistic Single-Task Continuous Learning Research for NER
- VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
- Meta-Learning Sparse Implicit Neural Representations
- Stabilising viscous extensional flows using Reinforcement Learning
- Improving Super-Resolution Performance using Meta-Attention Layers
- Pay attention to emoji: Feature Fusion Network with EmoGraph2vec Model for Sentiment Analysis
- Similarity and Matching of Neural Network Representations
- (Almost) Free Incentivized Exploration from Decentralized Learning Agents
- Scalable Bayesian Network Structure Learning with Splines
- Entropy-based adaptive Hamiltonian Monte Carlo
- Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
- Fairer LP-based Online Allocation via Analytic Center
- Play to Grade: Testing Coding Games as Classifying Markov Decision Process
- International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines
- Towards a Theory of Evolution as Multilevel Learning
- End-to-end LSTM based estimation of volcano event epicenter localization
- TA-Net: Topology-Aware Network for Gland Segmentation
- TMBuD: A dataset for urban scene building detection
- Fuzzy Generative Adversarial Networks
- Boundary Guided Context Aggregation for Semantic Segmentation
- Deep learning via message passing algorithms based on belief propagation
- Spatio-Temporal Federated Learning for Massive Wireless Edge Networks
- A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition
- IndoNLI: A Natural Language Inference Dataset for Indonesian
- V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL
- GenURL: A General Framework for Unsupervised Representation Learning
- Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons
- Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
- Comparing Heuristics, Constraint Optimization, and Reinforcement Learning for an Industrial 2D Packing Problem
- FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inference
- Model based Multi-agent Reinforcement Learning with Tensor Decompositions
- Active clustering for labeling training data
- NIDA-CLIFGAN: Natural Infrastructure Damage Assessment through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks
- Streaming Generalized Canonical Polyadic Tensor Decompositions
- Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations
- Deep Transfer Learning for Multi-source Entity Linkage via Domain Adaptation
- Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance
- Simple data balancing achieves competitive worst-group-accuracy
- Training Lightweight CNNs for Human-Nanodrone Proximity Interaction from Small Datasets using Background Randomization
- Fast rates for prediction with limited expert advice
- PL-Net: Progressive Learning Network for Medical Image Segmentation
All 220
- An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation
- DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention
- Hand gesture detection in tests performed by older adults
- Accelerating Gradient-based Meta Learner
- Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching
- CBIR using Pre-Trained Neural Networks
- Validation Methods for Energy Time Series Scenarios from Deep Generative Models
- Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding
- Spike-and-Slab LASSO Generalized Additive Models and Scalable Algorithms for High-Dimensional Data Analysis
- Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
- Failure-averse Active Learning for Physics-constrained Systems
- Predictive Geological Mapping with Convolution Neural Network Using Statistical Data Augmentation on a 3D Model
- Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme
- Exploring single-song autoencoding schemes for audio-based music structure analysis
- Nonnegative Tucker Decomposition with Beta-divergence for Music Structure Analysis of Audio Signals
- Iterative Teaching by Label Synthesis
- Adversarial Neuron Pruning Purifies Backdoored Deep Models
- The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning
- Locally Differentially Private Bayesian Inference
- Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data
- Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels
- Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning
- Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs
- Localized Super Resolution for Foreground Images using U-Net and MR-CNN
- Separating Content and Style for Unsupervised Image-to-Image Translation
- Learning where to learn: Gradient sparsity in meta and continual learning
- Can Linguistic Distance help Language Classification? Assessing Hawrami-Zaza and Kurmanji-Sorani
- A Preliminary Case Study of Planning With Complex Transitions: Plotting
- TaylorSwiftNet: Taylor Driven Temporal Modeling for Swift Future Frame Prediction
- Traffic Forecasting on Traffic Moving Snippets
- Temporal-attentive Covariance Pooling Networks for Video Recognition
- Towards artificial general intelligence via a multimodal foundation model
- Node Dependent Local Smoothing for Scalable Graph Learning
- Perceptual Score: What Data Modalities Does Your Model Perceive?
- A2I Transformer: Permutation-equivariant attention network for pairwise and many-body interactions with minimal featurization
- Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition
- ConAM: Confidence Attention Module for Convolutional Neural Networks
- VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
- Binarized ResNet: Enabling Robust Automatic Modulation Classification at the resource-constrained Edge
- MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data
- Enhancing Reinforcement Learning with discrete interfaces to learn the Dyck Language
- CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters
- A Scalable Inference Method For Large Dynamic Economic Systems
- Comprehensive learning particle swarm optimization enabled modeling framework for multi-step-ahead influenza prediction
- Active-LATHE: An Active Learning Algorithm for Boosting the Error Exponent for Learning Homogeneous Ising Trees
- Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias
- GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
- Multi-frequency image completion via a biologically-inspired sub-Riemannian model with frequency and phase
- Feature selection revisited in the single-cell era
- Node-wise Localization of Graph Neural Networks
- Ask "Who", Not "What": Bitcoin Volatility Forecasting with Twitter Data
- Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation
- Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks
- Denoising and change point localisation in piecewise-constant high-dimensional regression coefficients
- Revisiting Sanity Checks for Saliency Maps
- Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems
- A Subgame Perfect Equilibrium Reinforcement Learning Approach to Time-inconsistent Problems
- TopicNet: Semantic Graph-Guided Topic Discovery
- APPTeK: Agent-Based Predicate Prediction in Temporal Knowledge Graphs
- How Important is Importance Sampling for Deep Budgeted Training?
- Deep Learning For Prominence Detection In Children's Read Speech
- Counterfactual Shapley Additive Explanations
- SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
- Cascaded Classifier for Pareto-Optimal Accuracy-Cost Trade-Off Using off-the-Shelf ANNs
- Multilayer Lookahead: a Nested Version of Lookahead
- Learning Domain Invariant Representations in Goal-conditioned Block MDPs
- Online Selective Classification with Limited Feedback
- Tight FPT Approximation for Constrained k-Center and k-Supplier
- Dynamic population-based meta-learning for multi-agent communication with natural language
- 3rd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition
- Learning Graph Cellular Automata
- Emoji-based Co-attention Network for Microblog Sentiment Analysis
- RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images
- Sample Selection for Fair and Robust Training
- Learning Diverse Policies in MOBA Games via Macro-Goals
- Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects
- What Do We Mean by Generalization in Federated Learning?
- Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose
- How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
- FedPrune: Towards Inclusive Federated Learning
- Syllabic Quantity Patterns as Rhythmic Features for Latin Authorship Attribution
- Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning
- Denoised Non-Local Neural Network for Semantic Segmentation
- Encoder-Decoder Networks for Analyzing Thermal and Power Delivery Networks
- From Image to Imuge: Immunized Image Generation
- Smooth head tracking for virtual reality applications
- Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity
- Robust Contrastive Learning Using Negative Samples with Diminished Semantics
- RoMA: Robust Model Adaptation for Offline Model-based Optimization
- An Experimental Study of Permanently Stored Learned Clauses
- OpeNPDN: A Neural-network-based Framework for Power Delivery Network Synthesis
- Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models
- QU-net++: Image Quality Detection Framework for Segmentation of Medical 3D Image Stacks
- Federated Linear Contextual Bandits
- Diversity Enhanced Active Learning with Strictly Proper Scoring Rules
- Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding
- Training Verifiers to Solve Math Word Problems
- Does the Data Induce Capacity Control in Deep Learning?
- Identifying the key components in ResNet-50 for diabetic retinopathy grading from fundus images: a systematic investigation
- Dream to Explore: Adaptive Simulations for Autonomous Systems
- Differentially Private Federated Bayesian Optimization with Distributed Exploration
- Training Wasserstein GANs without gradient penalties
- Diversity Matters When Learning From Ensembles
- Uniform Concentration Bounds toward a Unified Framework for Robust Clustering
- Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
- Physically Explainable CNN for SAR Image Classification
- SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation
- Constrained Optimization Involving Nonconvex ℓp Norms: Optimality Conditions, Algorithm and Convergence
- Data-Driven Representations for Testing Independence: Modeling, Analysis and Connection with Mutual Information Estimation
- On Computing the Hyperparameter of Extreme Learning Machines: Algorithm and Application to Computational PDEs, and Comparison with Classical and High-Order Finite Elements
- ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
- Data-driven decomposition of brain dynamics with principal component analysis in different types of head impacts
- Mining frequency-based sequential trajectory co-clusters
- Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums
- Tight Concentrations and Confidence Sequences from the Regret of Universal Portfolio
- Provable Lifelong Learning of Representations
- Towards Robust Bisimulation Metric Learning
- Learning-Augmented k-means Clustering
- BioGrad: Biologically Plausible Gradient-Based Learning for Spiking Neural Networks
- Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories