activity
20062022
most citedBeyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

112 citations · 258 across the 12 of their papers we have counts for

collaborators

23 papers

cs.LG2022

Communication Efficient Federated Learning via Ordered ADMM in a Fully Decentralized Setting

Yicheng Chen, Rick S. Blum, Brian M. Sadler

The challenge of communication-efficient distributed optimization has attracted attention in recent years. In this paper, a communication efficient algorithm, called ordering-based…

cs.RO202141 cited

Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems

Amanda Prorok, Matthew Malencia, Luca Carlone +3

Robustness is key to engineering, automation, and science as a whole. However, the property of robustness is often underpinned by costly requirements such as over-provisioning, kno…

cs.LG202112 cited

Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping

Zhan Gao, Subhrajit Bhattacharya, Leiming Zhang +3

Graph neural networks (GNNs) are processing architectures that exploit graph structural information to model representations from network data. Despite their success, GNNs suffer f…

cs.RO20212 cited

Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks

Ting-Kuei Hu, Fernando Gama, Tianlong Chen +4

In this paper, we present a perception-action-communication loop design using Vision-based Graph Aggregation and Inference (VGAI). This multi-agent decentralized learning-to-contro…

eess.SP2021

Physical-Layer Security via Distributed Beamforming in the Presence of Adversaries with Unknown Locations

Yagiz Savas, Abolfazl Hashemi, Abraham P. Vinod +2

We study the problem of securely communicating a sequence of information bits with a client in the presence of multiple adversaries at unknown locations in the environment. We assu…

cs.CL2020112 cited

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

Yu Gu, Sue Kase, Michelle Vanni +4

Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the te…