activity
20182021
most citedEgo-GNNs: Exploiting Ego Structures in Graph Neural Networks

11 citations · 20 across the 4 of their papers we have counts for

collaborators

9 papers

cs.LG2021

Semi-Supervised Deep Learning for Multiplex Networks

Anasua Mitra, Priyesh Vijayan, Ranbir Sanasam +3

Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer.…

cs.LG202111 cited

Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks

Dylan Sandfelder, Priyesh Vijayan, William L. Hamilton

Graph neural networks (GNNs) have achieved remarkable success as a framework for deep learning on graph-structured data. However, GNNs are fundamentally limited by their tree-struc…

cs.CL2020

On Incorporating Structural Information to improve Dialogue Response Generation

Nikita Moghe, Priyesh Vijayan, Balaraman Ravindran +1

We consider the task of generating dialogue responses from background knowledge comprising of domain specific resources. Specifically, given a conversation around a movie, the task…

cs.CV2020

Understanding Dynamic Scenes using Graph Convolution Networks

Sravan Mylavarapu, Mahtab Sandhu, Priyesh Vijayan +3

We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed b…

cs.CV2020

Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks

Sravan Mylavarapu, Mahtab Sandhu, Priyesh Vijayan +3

Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity. In this paper, we propose a pipeline for understanding vehicle behaviour f…

cs.SI2019

Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling

Harshavardhan Kamarthi, Priyesh Vijayan, Bryan Wilder +2

A serious challenge when finding influential actors in real-world social networks is the lack of knowledge about the structure of the underlying network. Current state-of-the-art m…