Shagun Sodhani

Attending Over Triads for Learning Signed Network Embedding

2019 · Frontiers in Big Data

Network embedding, which aims at learning distributed representations for nodes in networks, is a critical task with wide downstream applications. Most existing studies focus on networks with a single type of edges, whereas in many …

A Closer Look at Codistillation for Distributed Training

2020 · arXiv (Cornell University)

Codistillation has been proposed as a mechanism to share knowledge among concurrently trained models by encouraging them to represent the same function through an auxiliary loss. This contrasts with the more commonly used fully-synchronous data-parallel …