5 papers
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion
Shervin Khalafi, Igor Krawczuk, Sergio Rozada +3
Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures like graph transformers have recently sh…
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
Shervin Khalafi, Alejandro Ribeiro, Dongsheng Ding
Unlearning in diffusion models aims to remove undesirable data or concepts while preserving the utility of pretrained models -- two fundamentally conflicting objectives. We propose…
Composition and Alignment of Diffusion Models using Constrained Learning
Shervin Khalafi, Ignacio Hounie, Dongsheng Ding +1
Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions. To improve the quality of generated samples and their compl…
Constrained Diffusion Models via Dual Training
Shervin Khalafi, Dongsheng Ding, Alejandro Ribeiro
Diffusion models have attained prominence for their ability to synthesize a probability distribution for a given dataset via a diffusion process, enabling the generation of new dat…
Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs
Shervin Khalafi, Saurabh Sihag, Alejandro Ribeiro
Neural tangent kernels (NTKs) provide a theoretical regime to analyze the learning and generalization behavior of over-parametrized neural networks. For a supervised learning task,…