ExpertNet: A Symbiosis of Classification and Clustering

01/17/2022
by   shivin-srivastava, et al.
0

A widely used paradigm to improve the generalization performance of high-capacity neural models is through the addition of auxiliary unsupervised tasks during supervised training. Tasks such as similarity matching and input reconstruction have been shown to provide a beneficial regularizing effect by guiding representation learning. Real data often has complex underlying structures and may be composed of heterogeneous subpopulations that are not learned well with current approaches. In this work, we design ExpertNet, which uses novel training strategies to learn clustered latent representations and leverage them by effectively combining cluster-specific classifiers. We theoretically analyze the effect of clustering on its generalization gap, and empirically show that clustered latent representations from ExpertNet lead to disentangling the intrinsic structure and improvement in classification performance. ExpertNet also meets an important real-world need where classifiers need to be tailored for distinct subpopulations, such as in clinical risk models. We demonstrate the superiority of ExpertNet over state-of-the-art methods on 6 large clinical datasets, where our approach leads to valuable insights on group-specific risks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/23/2021

CAC: A Clustering Based Framework for Classification

In data containing heterogeneous subpopulations, classification performa...
research
11/19/2019

Deep Unsupervised Clustering with Clustered Generator Model

This paper addresses the problem of unsupervised clustering which remain...
research
10/05/2021

Semi-Supervised Deep Learning for Multiplex Networks

Multiplex networks are complex graph structures in which a set of entiti...
research
05/20/2022

Towards Explanation for Unsupervised Graph-Level Representation Learning

Due to the superior performance of Graph Neural Networks (GNNs) in vario...
research
10/18/2022

Towards Efficient and Effective Self-Supervised Learning of Visual Representations

Self-supervision has emerged as a propitious method for visual represent...
research
04/05/2021

Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purification

Deep Learning models are highly susceptible to adversarial manipulations...
research
12/02/2022

Improved Representation Learning Through Tensorized Autoencoders

The central question in representation learning is what constitutes a go...

Please sign up or login with your details

Forgot password? Click here to reset