Leveraging tensor kernels to reduce objective function mismatch in deep clustering

• URL: http://arxiv.org/abs/2001.07026v3
• Date: Tue, 13 Feb 2024 08:09:00 GMT
• Title: Leveraging tensor kernels to reduce objective function mismatch in deep clustering
• Authors: Daniel J. Trosten, Sigurd L{\o}kse, Robert Jenssen, Michael Kampffmeyer
• Abstract summary: Objective Function Mismatch (OFM) occurs when the optimization of one objective has a negative impact on another objective. In this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to reduced clustering performance. To reduce the mismatch, while maintaining the structure-preserving property of an auxiliary objective, we propose a set of new auxiliary objectives.
• Score: 19.09439997799764
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Objective Function Mismatch (OFM) occurs when the optimization of one objective has a negative impact on the optimization of another objective. In this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to both reduced clustering performance, and a significant amount of OFM between the reconstruction and clustering objectives. To reduce the mismatch, while maintaining the structure-preserving property of an auxiliary objective, we propose a set of new auxiliary objectives for deep clustering, referred to as the Unsupervised Companion Objectives (UCOs). The UCOs rely on a kernel function to formulate a clustering objective on intermediate representations in the network. Generally, intermediate representations can include other dimensions, for instance spatial or temporal, in addition to the feature dimension. We therefore argue that the na\"ive approach of vectorizing and applying a vector kernel is suboptimal for such representations, as it ignores the information contained in the other dimensions. To address this drawback, we equip the UCOs with structure-exploiting tensor kernels, designed for tensors of arbitrary rank. The UCOs can thus be adapted to a broad class of network architectures. We also propose a novel, regression-based measure of OFM, allowing us to accurately quantify the amount of OFM observed during training. Our experiments show that the OFM between the UCOs and the main clustering objective is lower, compared to a similar autoencoder-based model. Further, we illustrate that the UCOs improve the clustering performance of the model, in contrast to the autoencoder-based approach. The code for our experiments is available at https://github.com/danieltrosten/tk-uco.

Related papers

• Self-Supervised Graph Embedding Clustering [70.36328717683297]
  K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. We propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework.
  arXiv  Detail & Related papers  (2024-09-24T08:59:51Z)
• OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation [69.37484603556307]
  Un Semantic segmenting (USS) involves segmenting images without relying on predefined labels. We introduce a novel approach called Optimally Matched Hierarchy (OMH) to simultaneously address the above issues. Our OMH yields better unsupervised segmentation performance compared to existing USS methods.
  arXiv  Detail & Related papers  (2024-03-11T09:46:41Z)
• A Generalized Framework for Predictive Clustering and Optimization [18.06697544912383]
  Clustering is a powerful and extensively used data science tool. In this article, we define a generalized optimization framework for predictive clustering. We also present a joint optimization strategy that exploits mixed-integer linear programming (MILP) for global optimization.
  arXiv  Detail & Related papers  (2023-05-07T19:56:51Z)
• Multi-View Clustering via Semi-non-negative Tensor Factorization [120.87318230985653]
  We develop a novel multi-view clustering based on semi-non-negative tensor factorization (Semi-NTF) Our model directly considers the between-view relationship and exploits the between-view complementary information. In addition, we provide an optimization algorithm for the proposed method and prove mathematically that the algorithm always converges to the stationary KKT point.
  arXiv  Detail & Related papers  (2023-03-29T14:54:19Z)
• DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering [6.447863458841379]
  This study introduces a lightweight Graph Neural Network (GNN) to replace classical clustering methods. Unlike existing methods, our GNN takes both the pair-wise affinities between local image features and the raw features as input. We demonstrate how classical clustering objectives can be formulated as self-supervised loss functions for training an image segmentation GNN.
  arXiv  Detail & Related papers  (2022-12-12T12:31:46Z)
• Deep Attention-guided Graph Clustering with Dual Self-supervision [49.040136530379094]
  We propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC) We develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Our method consistently outperforms state-of-the-art methods on six benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-10T06:53:03Z)
• Deep Embedded K-Means Clustering [1.5697094704362897]
  Key idea is that representation learning and clustering can reinforce each other. In this paper, we propose DEKM (for Deep Embedded K-Means) to answer these two questions. Experimental results on the real-world datasets demonstrate that DEKM achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-09-30T14:12:59Z)
• Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
  Variational autoencoders (VAE) are a powerful and widely-used class of generative models. We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
  arXiv  Detail & Related papers  (2021-01-06T17:36:26Z)
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
  Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain. We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one. Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
  arXiv  Detail & Related papers  (2020-12-08T08:52:00Z)
• Joint Optimization of an Autoencoder for Clustering and Embedding [22.16059261437617]
  We present an alternative where the autoencoder and the clustering are learned simultaneously. That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model.
  arXiv  Detail & Related papers  (2020-12-07T14:38:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.