Neural network-based clustering using pairwise constraints

11/19/2015
by   Yen-Chang Hsu, et al.
0

This paper presents a neural network-based end-to-end clustering framework. We design a novel strategy to utilize the contrastive criteria for pushing data-forming clusters directly from raw data, in addition to learning a feature embedding suitable for such clustering. The network is trained with weak labels, specifically partial pairwise relationships between data instances. The cluster assignments and their probabilities are then obtained at the output layer by feed-forwarding the data. The framework has the interesting characteristic that no cluster centers need to be explicitly specified, thus the resulting cluster distribution is purely data-driven and no distance metrics need to be predefined. The experiments show that the proposed approach beats the conventional two-stage method (feature embedding with k-means) by a significant margin. It also compares favorably to the performance of the standard cross entropy loss for classification. Robustness analysis also shows that the method is largely insensitive to the number of clusters. Specifically, we show that the number of dominant clusters is close to the true number of clusters even when a large k is used for clustering.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/11/2018

Learning Neural Models for End-to-End Clustering

We propose a novel end-to-end neural network architecture that, once tra...
research
03/16/2022

Is it all a cluster game? – Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space

It is essential for safety-critical applications of deep neural networks...
research
10/01/2019

Deep Lifetime Clustering

The goal of lifetime clustering is to develop an inductive model that ma...
research
11/20/2019

Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement

Identifying new user intents is an essential task in the dialogue system...
research
09/27/2020

NN-EVCLUS: Neural Network-based Evidential Clustering

Evidential clustering is an approach to clustering based on the use of D...
research
06/25/2015

CRAFT: ClusteR-specific Assorted Feature selecTion

We present a framework for clustering with cluster-specific feature sele...
research
05/29/2023

DMS: Differentiable Mean Shift for Dataset Agnostic Task Specific Clustering Using Side Information

We present a novel approach, in which we learn to cluster data directly ...

Please sign up or login with your details

Forgot password? Click here to reset