↓Skip to main content

Machine Learning

RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
·2296 words·11 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 the George Washington University
RGMDT algorithm extracts high-performing, interpretable decision trees from deep RL policies, guaranteeing near-optimal returns with size constraints, and extending to multi-agent settings.
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
·2189 words·11 mins· loading · loading
Machine Learning Federated Learning 🏢 National University of Singapore
RFLPA: Secure Federated Learning resists poisoning attacks via efficient secure aggregation.
Reward Machines for Deep RL in Noisy and Uncertain Environments
·2032 words·10 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 University of Toronto
Deep RL agents can now effectively learn complex tasks even with noisy, uncertain sensor readings by exploiting the structure of Reward Machines.
Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
·2405 words·12 mins· loading · loading
Machine Learning Deep Learning 🏢 School of Artificial Intelligence, Shanghai Jiao Tong University
Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation dynamically adjusts class weights during training using density ratio estimation, significantly improving model generalization, e…
Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective
·1781 words·9 mins· loading · loading
Machine Learning Self-Supervised Learning 🏢 National University of Singapore
SCHOOL: A novel SHGL framework enhancing spectral clustering with rank and dual consistency constraints, effectively mitigating noise and leveraging cluster-level information for improved downstream t…
Revisiting Score Propagation in Graph Out-of-Distribution Detection
·2721 words·13 mins· loading · loading
Machine Learning Semi-Supervised Learning 🏢 College of Computer Science and Technology, Zhejiang University
GRASP: A novel graph augmentation strategy boosts OOD node detection by strategically adding edges to enhance the intra-edge ratio, addressing score propagation’s limitations in various scenarios.
Revisiting Ensembling in One-Shot Federated Learning
·3849 words·19 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 EPFL
FENS: a novel federated ensembling scheme that boosts one-shot federated learning accuracy to near iterative FL levels, while maintaining low communication costs.
Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
·2081 words·10 mins· loading · loading
AI Generated Machine Learning Transfer Learning 🏢 School of Computing, Macquarie University
I-Div accurately quantifies distribution discrepancy between training and test datasets without test labels, enabling reliable hypothesis applicability evaluation in complex scenarios.
Retrieval-Augmented Diffusion Models for Time Series Forecasting
·2360 words·12 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 Peking University
Boosting time series forecasting accuracy, Retrieval-Augmented Diffusion Models (RATD) leverage relevant historical data to guide the diffusion process, overcoming limitations of existing models and d…
Retrieval & Fine-Tuning for In-Context Tabular Models
·3508 words·17 mins· loading · loading
Machine Learning Deep Learning 🏢 Layer6
LoCalPFN: boosting in-context tabular learning via retrieval & fine-tuning!
Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks
·2616 words·13 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 College of Artificial Intelligence, Southwest University
Boosting spiking neural network accuracy by 4.05% on ImageNet and achieving state-of-the-art results on CIFAR10-DVS and N-Caltech101 through learnable initial membrane potential and refined training s…
Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective
·3317 words·16 mins· loading · loading
Machine Learning Unsupervised Learning 🏢 Zhejiang University
NewImp boosts diffusion models’ missing data imputation by curbing sample diversity and eliminating data masking, achieving superior accuracy.
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
·2177 words·11 mins· loading · loading
Machine Learning Representation Learning 🏢 Korea Advanced Institute of Science and Technology (KAIST)
MUSE, a novel graph anomaly detection method, leverages multifaceted summaries of reconstruction errors, achieving state-of-the-art performance by addressing limitations of existing Graph-AE-based met…
Rethinking Optimal Transport in Offline Reinforcement Learning
·2060 words·10 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 AIRI
Offline RL enhanced via Optimal Transport: A new algorithm stitches best expert behaviors for efficient policy extraction.
Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity
·1788 words·9 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 Peking University
Reinforcement learning paradigms exhibit a representation complexity hierarchy: models are easiest, then policies, and value functions are hardest to approximate.
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
·2568 words·13 mins· loading · loading
AI Generated Machine Learning Reinforcement Learning 🏢 Boston University
PAGAR: a novel semi-supervised IRL framework prioritizing task alignment over data alignment, leveraging expert demonstrations as weak supervision to derive task-aligned reward functions for improved …
Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting
·1994 words·10 mins· loading · loading
Machine Learning Deep Learning 🏢 School of Computing, Macquarie University
Revolutionizing long-term time series forecasting, a new Fourier Basis Mapping method enhances accuracy by precisely interpreting frequency coefficients and considering time-frequency relationships, a…
Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints
·2740 words·13 mins· loading · loading
Machine Learning Deep Learning 🏢 University of Southampton
Stable algorithm learning achieved by Deep Thinking networks with Lipschitz Constraints, ensuring convergence and better extrapolation to complex problems.
Resource-Aware Federated Self-Supervised Learning with Global Class Representations
·2832 words·14 mins· loading · loading
AI Generated Machine Learning Self-Supervised Learning 🏢 Shandong University
FedMKD: A multi-teacher framework for federated self-supervised learning, enabling global class representations even with diverse client models and skewed data distributions.
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
·3167 words·15 mins· loading · loading
AI Generated Machine Learning Continual Learning 🏢 University of Technology Sydney
Forget-free graph class-incremental learning achieved via a novel task profiling and prompting approach, significantly outperforming state-of-the-art methods.