paper-with-me

Papers

A Hybrid Supervised and Self-Supervised Graph Neural Network for Edge-Centric Applications

2025-01-21 · Eugenio Borzone, Leandro Di Persia, Matias Gerard

This paper presents a novel graph-based deep learning model for tasks involving relations between two nodes (edge-centric tasks), where the focus lies on predicting relationships and interactions between pairs of nodes rather than node properties themselves. This model combines supervised and self-supervised learning, taking into account for the loss function the embeddings learned and patterns with and without ground truth. Additionally it incorporates an attention mechanism that leverages both node and edge features. The architecture, trained end-to-end, comprises two primary components: embedding generation and prediction. First, a graph neural network (GNN) transform raw node features into dense, low-dimensional embeddings, incorporating edge attributes. Then, a feedforward neural model processes the node embeddings to produce the final output. Experiments demonstrate that our model matches or exceeds existing methods for protein-protein interactions prediction and Gene Ontology (GO) terms prediction. The model also performs effectively with one-hot encoding for node features, providing a solution for the previously unsolved problem of predicting similarity between compounds with unknown structures.

📄 PDF Abstract BibTeX arXiv:2501.12309

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural NetworkPredictionSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Ontology 설명 없음
Graph Neural Network 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Few Edges Are Enough: Few-Shot Network Attack Detection with Graph Neural Networks

2025-01-28 · Tristan Bilot, Nour El Madhoun, Khaldoun Al Agha, Anis Zouaoui

Detecting cyberattacks using Graph Neural Networks (GNNs) has seen promising results recently. Most of the state-of-the-art models that leverage these techniques require labeled examples, hard to obtain in many real-worl…

Few-Shot LearningSelf-Supervised Learning

Hybrid-supervised Hypergraph-enhanced Transformer for Micro-gesture Based Emotion Recognition

2025-07-20 · Zhaoqiang Xia, Hexiang Huang, Haoyu Chen, Xiaoyi Feng 외 arxiv

Micro-gestures are unconsciously performed body gestures that can convey the emotion states of humans and start to attract more research attention in the fields of human behavior understanding and affective computing as …

Self-Supervised LearningEmotion Recognition

Graph Self-Supervised Learning: A Survey

2021-02-27 · Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou 외

Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization,…

Self-Supervised LearningSurvey

Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification

2021-10-09 · Jinghan Sun, Dong Wei, Kai Ma, Liansheng Wang 외

Rare diseases are characterized by low prevalence and are often chronically debilitating or life-threatening. Imaging-based classification of rare diseases is challenging due to the severe shortage in training examples. …

ClassificationFew-Shot LearningPseudo LabelRepresentation Learning

Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment

2022-11-23 · Yuchen Ma, Yanbei Chen, Zeynep Akata

Recent advances have indicated the strengths of self-supervised pre-training for improving representation learning on downstream tasks. Existing works often utilize self-supervised pre-trained models by fine-tuning on do…

Knowledge DistillationRepresentation LearningSelf-Supervised Learning