Kolmogorov-Arnold Networks for Personal Context Recognition on ExtraSensory

2026-10-04

AI Summary

This study addresses the challenge of balancing model performance and computational efficiency in personal context recognition by systematically evaluating Kolmogorov-Arnold Networks (KAN) and their variants on tabular data-driven context recognition tasks. Using the ExtraSensory dataset, ablation studies are conducted to compare KAN against multilayer perceptrons (MLPs) and TabM. The results demonstrate that KAN significantly outperforms traditional MLPs while achieving performance comparable to TabM, effectively validating its architectural advantages for tabular context recognition. Although KAN incurs relatively higher training overhead, this work provides important empirical evidence for exploring lightweight context-aware models that combine high expressiveness with practical utility.

Abstract

Kolmogorov--Arnold Networks (KANs) have attracted increasing attention in recent years, with applications across a wide range of AI tasks. In this paper, we evaluate several KAN variants on the ExtraSensory dataset for personal context recognition and compare them with a multilayer perceptron (MLP) and TabM. We conduct the main experiments using five user folds and three random seeds per fold and report the average Macro-F1, Micro-F1, and training time. We also perform shallow ablation studies on grid size, the number of grids, and data normalization to examine their effects on KAN performance. The results show that all evaluated KAN variants significantly outperform MLP in terms of Macro-F1 and Micro-F1 and achieve performance comparable to TabM. However, KAN variants generally require more training time, while TabM provides a more favorable balance between predictive performance and training efficiency. These results suggest that KANs are promising for personal context recognition, while their computational efficiency remains an important challenge. Our source code is publicly available at: https://github.com/hoangthangta/ExtraSensory-KANs.

Problem

• Personal Context Recognition
• Kolmogorov-Arnold Networks
• ExtraSensory dataset
• Computational efficiency

Innovation

• Kolmogorov-Arnold Networks
• Personal Context Recognition
• ExtraSensory Dataset
• Ablation Study
• TabM