# Neural network-based clustering using pairwise constraints

@article{Hsu2015NeuralNC, title={Neural network-based clustering using pairwise constraints}, author={Yen-Chang Hsu and Zsolt Kira}, journal={ArXiv}, year={2015}, volume={abs/1511.06321} }

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… Expand

#### Supplemental Code

Github Repo

Via Papers with Code

The demo code for "Neural network-based clustering using pairwise constraints" (http://arxiv.org/abs/1511.06321)

#### 51 Citations

ClusterNet : Semi-Supervised Clustering using Neural Networks

- Computer Science
- ArXiv
- 2018

A new loss function is defined that uses pairwise semantic similarity between objects combined with constrained k-means clus- tering to efficiently utilize both labeled and unlabeled data in the same framework. Expand

Semi-Supervised Clustering with Neural Networks

- Computer Science, Mathematics
- 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM)
- 2020

A new loss function is defined that uses pairwise semantic similarity between objects combined with constrained k-means clustering to efficiently utilize both labeled and unlabeled data in the same framework. Expand

Constrained Spectral Clustering Network with Self-Training

- Computer Science
- 2020 25th International Conference on Pattern Recognition (ICPR)
- 2021

A novel framework of Constrained Spectral Clustering Network (CSCN) is proposed by incorporating pairwise constraints and clustering oriented fine-tuning to deal with the ill-posedness of deep spectral clustering. Expand

Clustering-Driven Deep Embedding With Pairwise Constraints

- Computer Science, Medicine
- IEEE Computer Graphics and Applications
- 2019

This paper proposes a new framework, called Clustering-driven deep embedding with PAirwise Constraints (CPAC), for nonparametric clustering using a neural network, based on a Siamese network and shows that clustering performance increases when using this scheme, even with a limited amount of user queries. Expand

AutoClustering: A Feed-Forward Neural Network Based Clustering Algorithm

- Computer Science
- 2018 IEEE International Conference on Data Mining Workshops (ICDMW)
- 2018

A novel clustering method realized only by a feed-forward neural network is discussed, which naturally provides the number of clusters as a number of unique one-hot vectors obtained as a result. Expand

A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints

- Computer Science, Mathematics
- Neural Networks
- 2020

This paper decomposes semi-supervised clustering into two simpler classification tasks: the first stage uses a pair of Siamese neural networks to label the unlabeled pairs of points as must-link or cannot-link; the second stage uses the fully pairwise-labeled dataset produced by the firststage in a supervised neural-network-based clustering method. Expand

A probabilistic constrained clustering for transfer learning and image category discovery

- Computer Science
- ArXiv
- 2018

A novel clustering formulation is provided to address scalability issues of previous work in terms of optimizing deeper networks and larger amounts of categories and demonstrates improved scalability and performance on both supervised learning and unsupervised transfer learning. Expand

TextCSN: a semi-supervised approach for text clustering using pairwise constraints and convolutional siamese network

- Computer Science
- SAC
- 2020

TextCSN is presented, a deep clustering approach that combines a Convolutional Siamese Network based on pairwise constraints to perform representation learning and the traditional K-Means algorithm for unsupervised clustering using the learned representation. Expand

A Framework for Deep Constrained Clustering

- Computer Science
- Data Min. Knowl. Discov.
- 2021

A deep learning framework for constrained clustering that can not only handle standard together/apart constraints (without the well documented negative effects reported earlier) generated from labeled side information but more complex constraints generated from new types of side information such as continuous values and high-level domain knowledge is explored. Expand

Input-Output Representations for Supervised Clustering Methods

- 2021

In this thesis, we explore solutions to the supervised clustering problem, focusing on neural network-based methods. We are motivated by problems such as semantic text summarization, topic… Expand

#### References

SHOWING 1-10 OF 45 REFERENCES

Learning A Task-Specific Deep Architecture For Clustering

- Computer Science, Mathematics
- SDM
- 2016

It is discovered that connecting deep learning to sparse coding benefits not only the model performance, but also its initialization and interpretation, leading to a carefully crafted deep model benefiting from both. Expand

Deep Embedding Network for Clustering

- Computer Science
- 2014 22nd International Conference on Pattern Recognition
- 2014

A deep embedding network for representation learning, which is more beneficial for clustering by considering two constraints on learned representations and applies a group sparsity constraint for the learned representations. Expand

Unsupervised Deep Embedding for Clustering Analysis

- Computer Science, Mathematics
- ICML
- 2016

Deep Embedded Clustering is proposed, a method that simultaneously learns feature representations and cluster assignments using deep neural networks and learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Expand

Learning Deep Representations for Graph Clustering

- Computer Science
- AAAI
- 2014

This work proposes a simple method, which first learns a nonlinear embedding of the original graph by stacked autoencoder, and then runs k-means algorithm on the embedding to obtain clustering result, which significantly outperforms conventional spectral clustering. Expand

Deep Linear Coding for Fast Graph Clustering

- Computer Science
- IJCAI
- 2015

This paper proposes a deep structure with a linear coder as the building block for fast graph clustering, called Deep Linear Coding (DLC), and jointly learns the feature transform function and discriminative codings, and guarantees that the learned codes are robust in spite of local distortions. Expand

Deep Learning with Nonparametric Clustering

- Computer Science
- ArXiv
- 2015

A deep belief network with nonparametric clustering that can learn features for clustering and infer model complexity in an unified framework and the experimental results show the advantage of the approach over competitive baselines. Expand

Constrained 1-Spectral Clustering

- Mathematics, Computer Science
- AISTATS
- 2012

This work presents a generalization of the popular spectral clustering technique which integrates cannot-link and must-link constraints and allows to optimize a trade-off between normalized cut and the number of violated constraints. Expand

Minkowski metric, feature weighting and anomalous cluster initializing in K-Means clustering

- Mathematics, Computer Science
- Pattern Recognit.
- 2012

The Minkowski metric based method is experimentally validated on datasets from the UCI Machine Learning Repository and generated sets of Gaussian clusters, and appears to be competitive in comparison with other K-Means based feature weighting algorithms. Expand

Auto-encoder Based Data Clustering

- Computer Science
- CIARP
- 2013

This paper proposes a new clustering method based on the auto-encoder network, which can learn a highly non-linear mapping function and can obtain stable and effective clustering. Expand

Clustering: A neural network approach

- Mathematics, Medicine
- Neural Networks
- 2010

A comprehensive overview of competitive learning based clustering methods is given and two examples are given to demonstrate the use of the clustering Methods. Expand