A hybrid KAN-MLP model for IMU-based human activity recognition achieves 5.33% relative macro F1 improvement over pure MLPs on eight datasets by placing KANs at input embedding and classification stages.
[Shiet al., 2026 ] Yuchen Shi, Qijun Hou, Pingyi Fan, and Khaled B
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
Proposes an inferential framework to test differences in categorical Gini correlations for predictor importance in classification, establishing asymptotic normality and consistency while accommodating unequal dimensions and dependence.
A POMDP formulation with spatio-temporal attention reinforcement learning improves federated client selection performance under partial visibility and data heterogeneity.
ADAPT is a new pre-training paradigm that aligns physical properties of time-series data to allow simultaneous training on 162 diverse classification datasets, achieving new state-of-the-art performance.
Data augmentations in contrastive learning are proved to be point estimates of positive-incentive noise, enabling a new learnable π-noise generator framework for augmentations.
citing papers explorer
-
KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition
A hybrid KAN-MLP model for IMU-based human activity recognition achieves 5.33% relative macro F1 improvement over pure MLPs on eight datasets by placing KANs at input embedding and classification stages.
-
Comparing Two Categorical Gini Correlations with Applications to Classification Problems
Proposes an inferential framework to test differences in categorical Gini correlations for predictor importance in classification, establishing asymptotic normality and consistency while accommodating unequal dimensions and dependence.
-
Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
A POMDP formulation with spatio-temporal attention reinforcement learning improves federated client selection performance under partial visibility and data heterogeneity.
-
ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification
ADAPT is a new pre-training paradigm that aligns physical properties of time-series data to allow simultaneous training on 162 diverse classification datasets, achieving new state-of-the-art performance.
-
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
Data augmentations in contrastive learning are proved to be point estimates of positive-incentive noise, enabling a new learnable π-noise generator framework for augmentations.
- Building a privacy-preserving Federated Recommender system for mobile devices
- MSTN: A Lightweight and Fast Model for General TimeSeries Analysis