IEEE

CSBNC-PAL: Consistency Semi-Supervised Brain Network Classification Framework With Prototypical-Adversarial Learning

Abstract: In recent years, semi-supervised learning (SSL) for functional brain network (FBN) classification has gained considerable attention due to its potential to leverage large amounts of ...
GitHub

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

This project investigates token quality from a noisy-label perspective and propose a generic token cleaning pipeline for SFT tasks. Our method filters out uninformative tokens while preserving those ...
GitHub

Fuzzy Equivalence–Driven Feature Selection with Constrained Sigmoid Similarity for Interpretable Supervised Learning

The code includes the core methodology, experimental results generation, and the script used to produce Table 4 from the manuscript. The framework is designed to be label-agnostic during similarity ...
IEEE

Relation-Aware Multiprototype Learning for Semi-Supervised Hyperspectral Image Classification

Abstract: Pseudo-label learning-based methods have achieved excellent performance by leveraging spatial–spectral features of massive unlabeled samples in hyperspectral image (HSI) classification.