🏢 University of Sydney
Learning the Latent Causal Structure for Modeling Label Noise
·2995 words·15 mins·
loading
·
loading
Machine Learning
Semi-Supervised Learning
🏢 University of Sydney
Learning latent causal structures improves label noise modeling by accurately estimating noise transition matrices without relying on similarity-based assumptions, leading to state-of-the-art classifi…
Entropy testing and its application to testing Bayesian networks
·328 words·2 mins·
loading
·
loading
AI Theory
Optimization
🏢 University of Sydney
This paper presents near-optimal algorithms for entropy identity testing, significantly improving Bayesian network testing efficiency.
Deep Graph Mating
·1581 words·8 mins·
loading
·
loading
Machine Learning
Transfer Learning
🏢 University of Sydney
Deep Graph Mating (GRAMA) enables training-free knowledge transfer in GNNs, achieving results comparable to pre-trained models without retraining or labeled data.
A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs
·2374 words·12 mins·
loading
·
loading
Federated Learning
🏢 University of Sydney
A-FedPD tackles federated learning’s ‘dual drift’ problem by aligning global and local dual variables, resulting in faster convergence and enhanced stability for primal-dual methods.