97 citations · 234 across the 26 of their papers we have counts for
4 papers · 1 filter
Set Twister for Single-hop Node Classification
Yangze Zhou, Vinayak Rao, Bruno Ribeiro
Node classification is a central task in relational learning, with the current state-of-the-art hinging on two key principles: (i) predictions are permutation-invariant to the orde…
Contextual Unsupervised Outlier Detection in Sequences
Mohamed A. Zahran, Leonardo Teixeira, Vinayak Rao +1
This work proposes an unsupervised learning framework for trajectory (sequence) outlier detection that combines ranking tests with user sequence models. The overall framework ident…
Relational Pooling for Graph Representations
Ryan L. Murphy, Balasubramaniam Srinivasan, Vinayak Rao +1
This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and diffusions. Our approach, denoted Relational Po…
Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
Ryan L. Murphy, Balasubramaniam Srinivasan, Vinayak Rao +1
We consider a simple and overarching representation for permutation-invariant functions of sequences (or multiset functions). Our approach, which we call Janossy pooling, expresses…