Learning Neural Models for End-to-End Clustering
This addresses the challenge of learnable clustering for researchers and practitioners in machine learning, though it appears incremental as it builds on existing neural and clustering methods.
The paper tackles the problem of clustering high-dimensional data by proposing an end-to-end neural network that outputs probabilistic cluster assignments in one pass, demonstrating promising performance on image and speech datasets like COIL-100 and TIMIT.
We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters $k$, and for each $1 \leq k \leq k_\mathrm{max}$, a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this ``learning to cluster'' and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.