Papers
Sat 5 Feb 2022
78 papers
- Improved Certified Defenses against Data Poisoning with (Deterministic) Finite AggregationLLM safety and security → Backdoor and data poisoning attacks
- Score-based Generative Modeling of Graphs via the System of Stochastic Differential EquationsDiffusion models → Flow matching, time series and science
- Rethinking ValueDice: Does It Really Improve Performance?Offline RL and imitation learning from data → Imitation learning methods
- Adversarially Trained Actor Critic for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation
- Speech Analysis for Automatic Mania Assessment in Bipolar Disorder
- Decision boundaries and convex hulls in the feature space that deep learning functions learn from images
- Backtrack Tie-Breaking for Decision Trees: A Note on Deodata Predictors
- Reinforcement learning for multi-item retrieval in the puzzle-based storage system
- Backdoor Defense via Decoupling the Training Process
- A Game-theoretic Understanding of Repeated Explanations in ML Models
- Deep-HyROMnet: A deep learning-based operator approximation for hyper-reduction of nonlinear parametrized PDEs
- A survey of top-down approaches for human pose estimation
- Doing Right by Not Doing Wrong in Human-Robot Collaboration
- A Graph Neural Network Framework for Grid-Based Simulation
- Beyond Black Box Densities: Parameter Learning for the Deviated Components
- Efficient Privacy Preserving Logistic Regression for Horizontally Distributed Data
- The Implicit Bias of Gradient Descent on Generalized Gated Linear Networks
- Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models
- RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verification
- The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
- Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces
- Classification on Sentence Embeddings for Legal Assistance
- Multilingual Hate Speech and Offensive Content Detection using Modified Cross-entropy Loss
- Improving Probabilistic Models in Text Classification via Active Learning
- Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework
- Training Differentially Private Models with Secure Multiparty Computation
- Adaptive Fine-Tuning of Transformer-Based Language Models for Named Entity Recognition
- DSSIM: a structural similarity index for floating-point data
- Privacy-preserving Speech Emotion Recognition through Semi-Supervised Federated Learning
- ROMNet: Renovate the Old Memories
- Exemplar-Based Contrastive Self-Supervised Learning with Few-Shot Class Incremental Learning
- Memory Defense: More Robust Classification via a Memory-Masking Autoencoder
- VIS-iTrack: Visual Intention through Gaze Tracking using Low-Cost Webcam
- Communication Efficient Federated Learning via Ordered ADMM in a Fully Decentralized Setting
- Causal Disentanglement for Semantics-Aware Intent Learning in Recommendation
- Differentially Private Graph Classification with GNNs
- Symmetric Volume Maps: Order-Invariant Volumetric Mesh Correspondence with Free Boundary
- Catch Me if You Can: A Novel Task for Detection of Covert Geo-Locations (CGL)
- LST: Lexicon-Guided Self-Training for Few-Shot Text Classification
- DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions
- Optimization of a Real-Time Wavelet-Based Algorithm for Improving Speech Intelligibility
- Unsupervised Point Cloud Pre-Training via Contrasting and Clustering
- TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials
- Science Facing Interoperability as a Necessary Condition of Success and Evil
- Multidimensional Cybersecurity Framework for Strategic Foresight
- Aspect-based Sentiment Analysis through EDU-level Attentions
- Graph Neural Network with Curriculum Learning for Imbalanced Node Classification
- LyaNet: A Lyapunov Framework for Training Neural ODEs
- PrivPAS: A real time Privacy-Preserving AI System and applied ethics
- LEAPMood: Light and Efficient Architecture to Predict Mood with Genetic Algorithm driven Hyperparameter Tuning
- Comparative study of 3D object detection frameworks based on LiDAR data and sensor fusion techniques
- Intent Contrastive Learning for Sequential Recommendation
- On the predictability in reversible steganography
- A Survey on Automated Sarcasm Detection on Twitter
- A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification
- A Survey on Poisoning Attacks Against Supervised Machine Learning
- Adversarial Detector with Robust Classifier
- A Coalition Formation Game Approach for Personalized Federated Learning
- GraphEye: A Novel Solution for Detecting Vulnerable Functions Based on Graph Attention Network
- Weisfeiler-Lehman meets Gromov-Wasserstein
- Distributed Learning With Sparsified Gradient Differences
- Investigating the Challenges of Class Imbalance and Scale Variation in Object Detection in Aerial Images
- LotRec: A Recommender for Urban Vacant Lot Conversion
- Semantic Similarity Computing Model Based on Multi Model Fine-Grained Nonlinear Fusion
- Importance Weighting Approach in Kernel Bayes' Rule
- Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification
- Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach
- MarkovGNN: Graph Neural Networks on Markov Diffusion
- Handling Distribution Shifts on Graphs: An Invariance Perspective
- ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning
- Minimax Optimal Algorithms with Fixed-k-Nearest Neighbors
- Linear Model Against Malicious Adversaries with Local Differential Privacy
- Spelunking the Deep: Guaranteed Queries on General Neural Implicit Surfaces via Range Analysis
- Machine Learning Method for Functional Assessment of Retinal Models
- Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations
- SEED: Sound Event Early Detection via Evidential Uncertainty
- Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation