Multi-Integration of Labels across Categories for Component Identification (MILCCI)

2026-02-04

arXiv.org

AI Summary

This work addresses the challenge of disentangling the independent contributions of multiple categorical labels to observed temporal data and identifying interpretable latent components. To this end, the authors propose a data-driven, sparse sequential decomposition method that explicitly models the time-varying dynamics of each component by integrating multi-label information. Leveraging intra-class label similarity, the approach enables fine-grained adjustment of component composition. A key innovation is the introduction of a label-driven cross-trial component alignment mechanism, which enhances interpretability and consistency across trials. The method demonstrates robust performance on both synthetic and real-world datasets—including neural recordings, voting behavior, and web browsing trends—accurately uncovering interpretable latent structures and elucidating the representational roles of multi-category labels.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Many fields collect large-scale temporal data through repeated measurements (trials), where each trial is labeled with a set of metadata variables spanning several categories. For example, a trial in a neuroscience study may be linked to a value from category (a): task difficulty, and category (b): animal choice. A critical challenge in time-series analysis is to understand how these labels are encoded within the multi-trial observations, and disentangle the distinct effect of each label entry across categories. Here, we present MILCCI, a novel data-driven method that i) identifies the interpretable components underlying the data, ii) captures cross-trial variability, and iii) integrates label information to understand each category's representation within the data. MILCCI extends a sparse per-trial decomposition that leverages label similarities within each category to enable subtle, label-driven cross-trial adjustments in component compositions and to distinguish the contribution of each category. MILCCI also learns each component's corresponding temporal trace, which evolves over time within each trial and varies flexibly across trials. We demonstrate MILCCI's performance through both synthetic and real-world examples, including voting patterns, online page view trends, and neuronal recordings.

Problem

• multi-category labels
• time-series analysis
• component identification
• cross-trial variability
• label encoding

Innovation

• multi-category label integration
• interpretable component identification
• cross-trial variability modeling
• sparse decomposition
• time-series analysis