Research map / Label-efficient and robust learning / Semi-supervised learning
Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data
Xiong Zhou, Xianming Liu, Hao Yu, Jialiang Wang, Zeke Xie, Junjun Jiang, Xiangyang Ji
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Variance-enlarged Poisson Learning (VPL), a graph-based semi-supervised learning framework that counters degenerate near-constant label functions when labels are extremely sparse.
Problem
Graph-based semi-supervised learning with extremely sparse labels often yields degenerate solutions where label functions are nearly constant over unlabeled nodes.
Approach
Introduces a variance-enlarging term into Poisson learning to alleviate degenerate solutions when labeled data is extremely scarce. Only the abstract was available, so details of the variance term are not stated here.
Experimental setup
Builds on: Poisson learning
Closest papers by meaning
- Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates (ICML 2020 · similarity 0.93)
- Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels (NeurIPS 2021 · similarity 0.90)
- PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning (AAAI 2021 · similarity 0.88)
- HGDL: Heterogeneous Graph Label Distribution Learning (NeurIPS 2024 · similarity 0.87)
- Unknown-Aware Graph Regularization for Robust Semi-supervised Learning from Uncurated Data (AAAI 2024 · similarity 0.86)
- Continuous Partitioning for Graph-Based Semi-Supervised Learning (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
