About
Blog
Pills
Software
Trainings
Seminar
⚲
Search results
Pill
Neural Collapse in deep classifiers during Terminal Phase of Training
Neural collapse refers to the observation that the last two layers of neural networks that were trained for a long time take a very simple, …
Pill
Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions
An investigation of common problems and pitfalls of the popular MMD technique for comparing distributions on graphs. Additionally, the …
Pill
Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning
A theoretical framework connecting data valuation scores, game theory and energy based models is presented. Common criteria like Shapley or …
Pill
Resolving Training Biases via Influence-based Data Relabeling
Influence functions are used to correct corrupt labels in a dataset that would significantly decrease a trained model’s performance. …
Pill
Understanding over-squashing and bottlenecks on graphs via curvature
Oversquashing refers to the struggling of graph neural networks with tasks requiring long-distance interactions between nodes. A new notion …
Pill
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
An analytic form for the de-noising process of diffusion neural networks is found in this important work. Monte Carlo sampling with the …
1
...
«
3
»
