• Home
  • Search
  • Select The Best: Enhancing Graph Representation with Adaptive Negative Sample Selection
  • https://doi.org/10.1109/icassp49357.2023.10095586Copy DOI Icon

Select The Best: Enhancing Graph Representation with Adaptive Negative Sample Selection

  • Jun 4, 2023
  • Xiangping Zheng +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Graph contrastive learning (GCL) has emerged as a powerful tool to address real-world widespread label scarcity problems and has achieved impressive success in the graph learning domain. Albeit their remarkable performance, most current works mainly focus on designing sample augmentation methods, while the effect of negative sample selection strategy is largely ignored by previous works but rather practical and significant for graph contrastive learning. In this paper, we study the impact of negative samples on learning graph-level representations, and innovatively propose a Reinforcement Graph Contrastive Learning (ReinGCL) for negative sample selection. To be concrete, our model consists of two major components: a graph contrastive learning framework (GCLF), and a selection distribution generator (SDG) for producing the selection probabilities based on RL. The key insight is that Re-inGCL attempts to leverage SDG to guide GCLF and narrow the divergence between the augmented positive pairs, so as to further improve graph representation learning. Extensive experiments demonstrate that our approach significantly yields superior performance compared to the state-of-the-art.

Similar Papers
  • Research Article
  • Citations32

MGCNSS: miRNA-disease association prediction with multi-layer graph convolution and distance-based negative sample selection strategy.

  • Mar 27, 2024
  • Briefings in bioinformatics
  • Zhen Tian +4
  • PDF
  • Research Article
  • Citations4

Predicting potential miRNA-disease associations based on more reliable negative sample selection

  • Oct 17, 2022
  • BMC Bioinformatics
  • Ruiyu Guo +4
  • PDF
  • Research Article

Research on positive and negative sample sampling strategies in contrastive learning

  • Nov 08, 2024
  • Applied and Computational Engineering
  • Wenyi Liu
  • Book Chapter
  • Citations3

MiRNA-Disease Associations Prediction Based on Negative Sample Selection and Multi-layer Perceptron

  • Jan 01, 2020
  • Na Li +4
  • Research Article

RetinaNet-XAG: Multi-Category SAR Target Detection Under Sample Imbalance With Oriented Bounding Boxes

  • Jan 01, 2025
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Shaofeng Li +5
  • PDF
  • Research Article
  • Citations3

Link prediction on bipartite networks using matrix factorization with negative sample selection.

  • Aug 16, 2023
  • PLOS ONE
  • Siqi Peng +2
  • PDF
  • Research Article
  • Citations1

Node classification in complex networks based on multi-view debiased contrastive learning

  • May 18, 2024
  • Complex & Intelligent Systems
  • Zhe Li +5
  • Research Article

Frequency Ratio–Guided Optimization of Negative Sample Selection and Sample Ratio for Landslide Susceptibility Assessment: A Case Study of the Heishui River Basin, China

  • Dec 29, 2025
  • Applied Sciences
  • Zhen Yang +5
  • Conference Article
  • Citations2361

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection

  • Jun 01, 2020
  • Shifeng Zhang +4
  • Research Article
  • Citations19

Inferring drug-disease associations by a deep analysis on drug and disease networks.

  • Jan 01, 2023
  • Mathematical Biosciences and Engineering
  • Lei Chen +2
  • PDF
  • Research Article
  • Citations70

Prediction of Drug Side Effects with a Refined Negative Sample Selection Strategy

  • May 09, 2020
  • Computational and Mathematical Methods in Medicine
  • Haiyan Liang +3
  • PDF
  • Research Article
  • Citations15

Improved cytokine\u2013receptor interaction prediction by exploiting the negative sample space

  • Oct 31, 2020
  • BMC Bioinformatics
  • Abhigyan Nath +1
  • Research Article
  • Citations12

An Adaptive Sample Assignment Network for Tiny Object Detection

  • Jan 01, 2024
  • IEEE Transactions on Multimedia
  • Honghao Dai +5
  • PDF
  • Research Article
  • Citations30

RNMFMDA: A Microbe-Disease Association Identification Method Based on Reliable Negative Sample Selection and Logistic Matrix Factorization With Neighborhood Regularization

  • Oct 27, 2020
  • Frontiers in Microbiology
  • Lihong Peng +4
  • Research Article
  • Citations5

Identifying Protein Phosphorylation Site-Disease Associations Based on Multi-Similarity Fusion and Negative Sample Selection by Convolutional Neural Network.

  • Mar 08, 2024
  • Interdisciplinary sciences, computational life sciences
  • Qian Deng +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.