output
20142026
most citedThroughput-Optimal Topology Design for Cross-Silo Federated Learning

50 citations

Showing 2021Show all

7 papers · 1 filter

cs.LG2021

Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods

Peru Bhardwaj, John Kelleher, Luca Costabello +1

Despite the widespread use of Knowledge Graph Embeddings (KGE), little is known about the security vulnerabilities that might disrupt their intended behaviour. We study data poison…

cs.CL20211 cited

Accenture at CheckThat! 2021: Interesting claim identification and ranking with contextually sensitive lexical training data augmentation

Evan Williams, Paul Rodrigues, Sieu Tran

This paper discusses the approach used by the Accenture Team for CLEF2021 CheckThat! Lab, Task 1, to identify whether a claim made in social media would be interesting to a wide au…

cs.AI20213 cited

Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes

Sumit Pai, Luca Costabello

Numeric values associated to edges of a knowledge graph have been used to represent uncertainty, edge importance, and even out-of-band knowledge in a growing number of scenarios, r…

cs.CV2021

VeriMedi: Pill Identification using Proxy-based Deep Metric Learning and Exact Solution

Tekin Evrim Ozmermer, Viktors Roze, Stanislavs Hilcuks +1

We present the system that we have developed for the identification and verification of pills using images that are taken by the VeriMedi device. The VeriMedi device is an Internet…

cs.LG20218 cited

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Lisa Schut, Oscar Key, Rory McGrath +4

Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions. For CEs to be useful, it is important that they…

cs.CY2021

A Framework for Enabling Safe and Resilient Food Factories for the Public Feeding Programs

Nataraj Kuntagod, Sanjay Podder, Satya Sai Srinivas Abbabathula +3

Public feeding programs continue to be a major source of nutrition to a large part of the population across the world. Any disruption to these activities, like the one during the C…