$\texttt{InfoHier}$: Hierarchical Information Extraction via Encoding and Embedding
This addresses the challenge of capturing multi-level relationships in real-world datasets like images for data analysis and information retrieval, representing an incremental hybrid approach.
The paper tackles the problem of analyzing complex high-dimensional datasets by proposing InfoHier, a framework that combines self-supervised learning with hierarchical clustering to jointly learn latent representations and hierarchical structures, resulting in improved expressiveness and performance for clustering and representation learning.
Analyzing large-scale datasets, especially involving complex and high-dimensional data like images, is particularly challenging. While self-supervised learning (SSL) has proven effective for learning representations from unlabelled data, it typically focuses on flat, non-hierarchical structures, missing the multi-level relationships present in many real-world datasets. Hierarchical clustering (HC) can uncover these relationships by organizing data into a tree-like structure, but it often relies on rigid similarity metrics that struggle to capture the complexity of diverse data types. To address these we envision $\texttt{InfoHier}$, a framework that combines SSL with HC to jointly learn robust latent representations and hierarchical structures. This approach leverages SSL to provide adaptive representations, enhancing HC's ability to capture complex patterns. Simultaneously, it integrates HC loss to refine SSL training, resulting in representations that are more attuned to the underlying information hierarchy. $\texttt{InfoHier}$ has the potential to improve the expressiveness and performance of both clustering and representation learning, offering significant benefits for data analysis, management, and information retrieval.