Search Results for author: Pascal Esser

Found 3 papers, 1 papers with code

When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?

no code implementations13 Mar 2024 Gautham Govind Anil, Pascal Esser, Debarghya Ghoshdastidar

We provide the first convergence results of NTK for contrastive losses, and present a nuanced picture: NTK of wide networks remains almost constant for cosine similarity based contrastive losses, but not for losses based on dot product similarity.

Contrastive Learning

Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel

1 code implementation18 Oct 2022 Mahalakshmi Sabanayagam, Pascal Esser, Debarghya Ghoshdastidar

The fundamental principle of Graph Neural Networks (GNNs) is to exploit the structural information of the data by aggregating the neighboring nodes using a `graph convolution' in conjunction with a suitable choice for the network architecture, such as depth and activation functions.

Node Classification Stochastic Block Model

New Insights into Graph Convolutional Networks using Neural Tangent Kernels

no code implementations8 Oct 2021 Mahalakshmi Sabanayagam, Pascal Esser, Debarghya Ghoshdastidar

This paper focuses on semi-supervised learning on graphs, and explains the above observations through the lens of Neural Tangent Kernels (NTKs).

Cannot find the paper you are looking for? You can Submit a new open access paper.