2020/10/02 by Samuel Coward, Coward, Samuel, Erik Visse-Martindale +3 · 2 citations
Computer Science · Mathematics · #Artificial intelligence #CURE data clustering algorithm #Cluster analysis #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Conceptual clustering #Context (archaeology) #Correlation clustering #Data Stream Mining Techniques #Data mining #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Geography #Kernel (algebra) #Kernel method #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Mathematics #Radial basis function kernel #Set (abstract data type) #Similarity (geometry) #String kernel #Support vector machine #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2010.01040
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/10/02 · openalex publication_date 2020/10/02 · arxiv updated 2020/10/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In machine learning, no data point stands alone. We believe that context is an underappreciated concept in many machine learning methods. We propose Attention-Based Clustering (ABC), a neural architecture based on the attention mechanism, which is designed to learn latent representations that adapt to context within an input set, and which is inherently agnostic to input sizes and number of clusters. By learning a similarity kernel, our method directly combines with any out-of-the-box kernel-based clustering approach. We present competitive results for clustering Omniglot characters and include analytical evidence of the effectiveness of an attention-based approach for clustering.