Semi Supervised Few Shot

Semi-supervised few-shot learning aims to train machine learning models that can accurately classify new data with minimal labeled examples, leveraging readily available unlabeled data to improve performance. Current research focuses on integrating large language models to enhance data representation and clustering, developing novel prototype-based and graph-based methods for label propagation and iterative graph refinement, and employing meta-learning strategies to adapt to diverse tasks with limited supervision. These advancements are significant because they enable efficient model training with scarce labeled data, impacting various applications where obtaining labeled data is expensive or time-consuming, such as image recognition and natural language processing.

Papers

July 2, 2023

Large Language Models Enable Few-Shot Clustering
Vijay Viswanathan, Kiril Gashteovski, Carolin Lawrence, Tongshuang Wu, Graham Neubig
Large Language Model Data Clustering Semi Supervised Clustering Semi Supervised Few Shot

April 23, 2023

Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement
Hao Zhu, Piotr Koniusz
Shot Learning Graph Structure Label Propagation Shot Task Transductive Few Shot Learning Semi Supervised Few Shot

March 2, 2023

Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning
Huiwon Jang, Hankook Lee, Jinwoo Shin
Self Supervised Meta Learning Unsupervised Setting Semi Supervised Meta Semi Supervised Few Shot

June 16, 2022

Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification
Xueliang Wang, Jianyu Cai, Shuiwang Ji, Houqiang Li, Feng Wu, Jie Wang
Shot Classification Label Augmentation Adaptive Metric Semi Supervised Few Shot

January 11, 2022

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning
Andrey Zhmoginov, Mark Sandler, Max Vladymyrov
LeArning Abstract Convolutional Neural Network Semi Supervised Transformer Based Model Convolutional Neural Network Model Model Generation Semi Supervised Few Shot

December 18, 2021

Meta Propagation Networks for Graph Few-shot Semi-supervised Learning
Kaize Ding, Jianling Wang, James Caverlee, Huan Liu
Pseudo Label Node Representation Label Propagation Graph Learning Task Shot Graph Semi Supervised Few Shot Meta Similarity Correction Network

October 21, 2021

A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
Linglan Zhao, Dashan Guo, Yunlu Xu, Liang Qiao, Zhanzhan Cheng, Shiliang Pu, Yi Niu, Xiangzhong Fang
Training Data Shot Learning Meta Learning Strong Baseline Semi Supervised Few Shot