Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding

About

Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve this performance, typically optimizing a clustering and non-clustering loss. In such cases, an autoencoder is typically connected with a clustering network, and the final clustering is jointly learned by both the autoencoder and clustering network. Instead, we propose to learn an autoencoded embedding and then search this further for the underlying manifold. For simplicity, we then cluster this with a shallow clustering algorithm, rather than a deeper network. We study a number of local and global manifold learning methods on both the raw data and autoencoded embedding, concluding that UMAP in our framework is best able to find the most clusterable manifold in the embedding, suggesting local manifold learning on an autoencoded embedding is effective for discovering higher quality discovering clusters. We quantitatively show across a range of image and time-series datasets that our method has competitive performance against the latest deep clustering algorithms, including out-performing current state-of-the-art on several. We postulate that these results show a promising research direction for deep clustering. The code can be found at https://github.com/rymc/n2d

Ryan McConville, Raul Santos-Rodriguez, Robert J Piechocki, Ian Craddock• 2019

Related benchmarks

TaskDatasetResultRank
ClusteringMNIST (test)
NMI0.882
122
ClusteringFashion MNIST
NMI68.4
95
Human Activity RecognitionREALDISP
F172.5
94
ClusteringMNIST
NMI0.942
92
ClusteringUSPS
NMI90.1
82
Image ClusteringUSPS
NMI0.9
43
ClusteringFashion (full)
ACC67.2
24
ClusteringMNIST original (train+test)
ACC97.9
16
ClusteringUSPS original (train+test)
Accuracy0.958
13
Human Activity RecognitionHHAR
F1 Score59.3
11
Showing 10 of 17 rows

Other info

Code

Follow for update