Papers
Mon 7 Feb 2022
199 papers
- VAEL: Bridging Variational Autoencoders and Probabilistic Logic ProgrammingLLM reasoning → Reasoning benchmarks and evaluation
- A Ranking Game for Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Deletion Inference, Reconstruction, and Compliance in Machine (Un)LearningLLM safety and security → Machine unlearning
- Membership Inference Attacks and Defenses in Neural Network PruningLLM safety and security → Membership inference attacks
- Red Teaming Language Models with Language ModelsLLM safety and security → Prompt injection and agent security
- Adaptive Mixing of Auxiliary Losses in Supervised LearningKnowledge distillation → General knowledge distillation methods
- Measuring and Reducing Model Update Regression in Structured Prediction for NLPKnowledge distillation → Knowledge distillation for LLMs
- Locally Differentially Private Distributed Deep Learning via Knowledge DistillationKnowledge distillation → Federated, robust and private distillation
- Learning from Imperfect Demonstrations via Adversarial Confidence TransferOffline RL and imitation learning from data → Imitation learning methods
- Model-Based Offline Meta-Reinforcement Learning with RegularizationOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Fine-Tuning Approach for Arabic Offensive Language Detection System: BERT-Based Model
- Quantification of Actual Road User Behavior on the Basis of Given Traffic Rules
- Artificial Intelligence-Based Analytics for Impacts of COVID-19 and Online Learning on College Students' Mental Health
- Minimizing Entropy to Discover Good Solutions to Recurrent Mixed Integer Programs
- Fabricated Flips: Poisoning Federated Learning without Data
- A Multi-Domain VNE Algorithm based on Load Balancing in the IoT networks
- EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
- DeepSSN: a deep convolutional neural network to assess spatial scene similarity
- RECOVER: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro
- Speech Emotion Recognition using Self-Supervised Features
- Accurate super-resolution low-field brain MRI
- Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning with Pairwise Alignment
- Attacking c-MARL More Effectively: A Data Driven Approach
- data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
- HeadPosr: End-to-end Trainable Head Pose Estimation using Transformer Encoders
- LwPosr: Lightweight Efficient Fine-Grained Head Pose Estimation
- Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling
- On Continuous Integration / Continuous Delivery for Automated Deployment of Machine Learning Models using MLOps
- SliTraNet: Automatic Detection of Slide Transitions in Lecture Videos using Convolutional Neural Networks
- Structured Time Series Prediction without Structural Prior
- Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably
- MINER: Multiscale Implicit Neural Representations
- TACTiS: Transformer-Attentional Copulas for Time Series
- Integrated Multiscale Domain Adaptive YOLO
- Nesterov Accelerated Shuffling Gradient Method for Convex Optimization
- Finite-Sum Optimization: A New Perspective for Convergence to a Global Solution
- Stakeholder utility measures for declarative processes and their use in process comparisons
- Smoothed Online Optimization with Unreliable Predictions
- Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study
- Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images
- Random Ferns for Semantic Segmentation of PolSAR Images
- DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning
- Approximation Algorithms for ROUND-UFP and ROUND-SAP
- Targeted-BEHRT: Deep learning for observational causal inference on longitudinal electronic health records
- Optimizing Warfarin Dosing using Deep Reinforcement Learning
- Self-supervised Speaker Recognition Training Using Human-Machine Dialogues
- MAML and ANIL Provably Learn Representations
- Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
- Universal Spam Detection using Transfer Learning of BERT Model
- Random Gegenbauer Features for Scalable Kernel Methods
- Random Alloy Codes and the Fundamental Limits of Coded Distributed Tensors
- Reward-Respecting Subtasks for Model-Based Reinforcement Learning
- On learning Whittle index policy for restless bandits with scalable regret
- Selecting Seed Words for Wordle using Character Statistics
- Multi-modal data generation with a deep metric variational autoencoder
- A Coarse-to-fine Morphological Approach With Knowledge-based Rules and Self-adapting Correction for Lung Nodules Segmentation
- Inference of captions from histopathological patches
- A Topology-Attention ConvLSTM Network and Its Application to EM Images
- VNE Strategy based on Chaotic Hybrid Flower Pollination Algorithm Considering Multi-criteria Decision Making
- A Reliable Data-transmission Mechanism using Blockchain in Edge Computing Scenarios
- Performance Evaluation of Infrared Image Enhancement Techniques
- Diversify and Disambiguate: Learning From Underspecified Data
- Deep Impulse Responses: Estimating and Parameterizing Filters with Deep Networks
- Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience
- Dependence model assessment and selection with DecoupleNets
- Preserving Privacy and Security in Federated Learning
- Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start
- Link Prediction of Artificial Intelligence Concepts using Low Computational Power
- Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery
- Geometric Multimodal Contrastive Representation Learning
- Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
- Corrupted Image Modeling for Self-Supervised Visual Pre-Training
- Benchmarking and Analyzing Point Cloud Classification under Corruptions
- Message Passing Neural PDE Solvers
- LEDNet: Joint Low-light Enhancement and Deblurring in the Dark
- Cedille: A large autoregressive French language model
- Simple Control Baselines for Evaluating Transfer Learning
- Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components
- Efficient Direct-Connect Topologies for Collective Communications
- Robust Dialogue State Tracking with Weak Supervision and Sparse Data
- Conditional Gradients for the Approximate Vanishing Ideal
- Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data
- FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbations
- Variance reduced stochastic optimization over directed graphs with row and column stochastic weights
- A Review of Landcover Classification with Very-High Resolution Remotely Sensed Optical Images-Analysis Unit,Model Scalability and Transferability
- Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences
- Robust Semantic Communications Against Semantic Noise
- Policy Optimization for Stochastic Shortest Path
- Optimal Ratio for Data Splitting
- Motion-Plane-Adaptive Inter Prediction in 360-Degree Video Coding
- A Robot Web for Distributed Many-Device Localisation
- Training OOD Detectors in their Natural Habitats
- Grassmann Stein Variational Gradient Descent
- Theoretical characterization of uncertainty in high-dimensional linear classification
- Mental Disorders on Online Social Media Through the Lens of Language and Behaviour: Analysis and Visualisation
- Approximation error of single hidden layer neural networks with fixed weights
- Gaussian Graphical Models as an Ensemble Method for Distributed Gaussian Processes
- CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors
- Personalized Public Policy Analysis in Social Sciences using Causal-Graphical Normalizing Flows
- Crafting Better Contrastive Views for Siamese Representation Learning
All 199
- On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks
- Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning
- Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration
- Confidence Guided Depth Completion Network
- AI-based artistic representation of emotions from EEG signals: a discussion on fairness, inclusion, and aesthetics
- Unsupervised physics-informed disentanglement of multimodal data for high-throughput scientific discovery
- Towards an Analytical Definition of Sufficient Data
- Introducing the Expohedron for Efficient Pareto-optimal Fairness-Utility Amortizations in Repeated Rankings
- Passive learning to address nonstationarity in virtual flow metering applications
- A Variational Edge Partition Model for Supervised Graph Representation Learning
- Neural Models for Output-Space Invariance in Combinatorial Problems
- HERMES: Hybrid Error-corrector Model with inclusion of External Signals for nonstationary fashion time series
- SODA: Self-organizing data augmentation in deep neural networks -- Application to biomedical image segmentation tasks
- Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition
- Introducing explainable supervised machine learning into interactive feedback loops for statistical production system
- PSSNet: Planarity-sensible Semantic Segmentation of Large-scale Urban Meshes
- Almost Optimal Proper Learning and Testing Polynomials
- Recent Trends in 2D Object Detection and Applications in Video Event Recognition
- More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks
- Field-of-View IoU for Object Detection in 360deg Images
- Towards Loosely-Coupling Knowledge Graph Embeddings and Ontology-based Reasoning
- CITRIS: Causal Identifiability from Temporal Intervened Sequences
- Bayesian Non-stationary Linear Bandits for Large-Scale Recommender Systems
- SLIDE: a surrogate fairness constraint to ensure fairness consistency
- Conversational Agents: Theory and Applications
- Patch-Based Stochastic Attention for Image Editing
- Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics
- Over-the-Air Ensemble Inference with Model Privacy
- Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
- To Tune or Not To Tune? Zero-shot Models for Legal Case Entailment
- Moving Other Way: Exploring Word Mover Distance Extensions
- Bubble identification from images with machine learning methods
- SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
- Combining Deep Learning and Reasoning for Address Detection in Unstructured Text Documents
- Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
- FL_PyTorch: optimization research simulator for federated learning
- Document-Level Event Extraction via Human-Like Reading Process
- Auto-Lambda: Disentangling Dynamic Task Relationships
- Unsupervised Long-Term Person Re-Identification with Clothes Change
- Machine Translation from Signed to Spoken Languages: State of the Art and Challenges
- Temporal Point Cloud Completion with Pose Disturbance
- Gender stereotypes in the mediated personalization of politics: Empirical evidence from a lexical, syntactic and sentiment analysis
- Fair Interpretable Representation Learning with Correction Vectors
- Adversarial Attack and Defense for Non-Parametric Two-Sample Tests
- Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation
- Distributionally Robust Fair Principal Components via Geodesic Descents
- Addressing modern and practical challenges in machine learning: A survey of online federated and transfer learning
- Artificial Intelligence based tool wear and defect prediction for special purpose milling machinery using low-cost acceleration sensor retrofits
- The Importance of Non-Markovianity in Maximum State Entropy Exploration
- Evaluation of Runtime Monitoring for UAV Emergency Landing
- Multi-Objective Quality Diversity Optimization
- Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods
- OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
- Using Partial Monotonicity in Submodular Maximization
- Data set creation and empirical analysis for detecting signs of depression from social media postings
- A new face swap method for image and video domains: a technical report
- Metric-valued regression
- Towards Learning Through Open-Domain Dialog
- Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
- Structure-Aware Transformer for Graph Representation Learning
- Human Stress Assessment: A Comprehensive Review of Methods Using Wearable Sensors and Non-wearable Techniques
- A comprehensive benchmark analysis for sand dust image reconstruction
- Context Autoencoder for Self-Supervised Representation Learning
- CECILIA: Comprehensive Secure Machine Learning Framework
- Algorithms that get old : the case of generative deep neural networks
- Learning Sound Localization Better From Semantically Similar Samples
- B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture Search
- Network Calculus with Flow Prolongation -- A Feedforward FIFO Analysis enabled by ML
- Automatic defect segmentation by unsupervised anomaly learning
- Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals
- Graph Self-supervised Learning with Accurate Discrepancy Learning
- Deep Residual Shrinkage Networks for EMG-based Gesture Identification
- Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
- 3D Object Detection from Images for Autonomous Driving: A Survey
- A Machine Learning Approach for Material Type Logging and Chemical Assaying from Autonomous Measure-While-Drilling (MWD) Data
- A comprehensive survey on computational learning methods for analysis of gene expression data
- Supervision by Denoising for Medical Image Segmentation
- Deep Deterministic Independent Component Analysis for Hyperspectral Unmixing
- Jury Learning: Integrating Dissenting Voices into Machine Learning Models
- Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networks
- Prompt-Guided Injection of Conformation to Pre-trained Protein Model
- Learning fair representation with a parametric integral probability metric
- Tractable Boolean and Arithmetic Circuits
- TRGP: Trust Region Gradient Projection for Continual Learning
- Towards Micro-video Thumbnail Selection via a Multi-label Visual-semantic Embedding Model
- ABG: A Multi-Party Mixed Protocol Framework for Privacy-Preserving Cooperative Learning
- Benchmarking Deep Models for Salient Object Detection
- Soft Actor-Critic with Inhibitory Networks for Faster Retraining
- Dataset Condensation with Contrastive Signals
- User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational Systems
- Universality of parametric Coupling Flows over parametric diffeomorphisms
- A Compressed Sensing Based Least Squares Approach to Semi-supervised Local Cluster Extraction
- Redactor: A Data-centric and Individualized Defense Against Inference Attacks
- Inter-subject Contrastive Learning for Subject Adaptive EEG-based Visual Recognition
- Gradient boosting machines and careful pre-processing work best: ASHRAE Great Energy Predictor III lessons learned
- Evaluation Methods and Measures for Causal Learning Algorithms
- Effects of Parametric and Non-Parametric Methods on High Dimensional Sparse Matrix Representations
- Lossy Compression of Noisy Data for Private and Data-Efficient Learning
- Causal Inference Using Tractable Circuits