activity
20122025
most citedFederated Learning with Only Positive Labels

40 citations · 165 across the 28 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

cs.IR2018

Comparative Document Summarisation via Classification

Umanga Bista, Alexander Mathews, Minjeong Shin +2

This paper considers extractive summarisation in a comparative setting: given two or more document groups (e.g., separated by publication time), the goal is to select a small numbe…

stat.ML2018

Complementary-Label Learning for Arbitrary Losses and Models

Takashi Ishida, Gang Niu, Aditya Krishna Menon +1

In contrast to the standard classification paradigm where the true class is given to each training pattern, complementary-label learning only uses training patterns each equipped w…

stat.ML2018

On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data

Nan Lu, Gang Niu, Aditya Krishna Menon +1

Empirical risk minimization (ERM), with proper loss function and regularization, is the common practice of supervised classification. In this paper, we study training arbitrary (fr…

cs.LG2018

Monge blunts Bayes: Hardness Results for Adversarial Training

Zac Cranko, Aditya Krishna Menon, Richard Nock +3

The last few years have seen a staggering number of empirical studies of the robustness of neural networks in a model of adversarial perturbations of their inputs. Most rely on an…

cs.LG2018

Anomaly Detection using One-Class Neural Networks

Raghavendra Chalapathy, Aditya Krishna Menon, Sanjay Chawla

We propose a one-class neural network (OC-NN) model to detect anomalies in complex data sets. OC-NN combines the ability of deep networks to extract a progressively rich representa…