paper-with-me

홈 › Papers

Fast and Featureless Node Representation Learning with Partial Pairwise Supervision

2026-05-19 · Sujan Chakraborty, Saptarshi Bej arxiv

We introduce Contrastive FUSE, a fast and unified framework for scalable node representation learning in graphs with partially available pairwise node labels and no available node features. Unlike existing methods, we directly optimize a spectral contrastive objective that integrates community-aware structural signals with signed pairwise constraints. To support large-scale training, we replace the expensive modularity gradient with a lightweight approximation, which preserves the structure-seeking behavior of modularity while reducing the computational cost significantly. This yields an efficient optimization scheme with a natural gradient decomposition and adaptive learning-rate scaling, enabling fast iterative updates even on million-edge graphs. Extensive experiments on benchmark citation networks, large co-purchase graphs, and OGB datasets show that Contrastive FUSE achieves competitive or superior contrastive classification performance without relying on node features, while offering substantial runtime gains over existing baselines. These results highlight the effectiveness of coupling modularity-inspired structural learning with contrastive supervision for efficient and scalable contrastive node representation learning.

📄 PDF Abstract BibTeX arXiv:2605.19916

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

A Robust Method for Image Stitching

2020-04-08 · Matti Pellikka, Valtteri Lahtinen

We propose a novel method for large-scale image stitching that is robust against repetitive patterns and featureless regions in the imagery. In such cases, state-of-the-art image stitching methods easily produce image al…

Image RegistrationImage Stitching

On Node Features for Graph Neural Networks

2019-11-20 · Chi Thang Duong, Thanh Dat Hoang, Ha The Hien Dang, Quoc Viet Hung Nguyen 외

Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neur…

Graph Neural NetworkGraph Representation LearningRepresentation Learning

Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification

2021-07-27 · Yu Wang, Yuesong Shen, Daniel Cremers

Node features and structural information of a graph are both crucial for semi-supervised node classification problems. A variety of graph neural network (GNN) based approaches have been proposed to tackle these problems,…

Graph Neural NetworkNode Classification

Spatial Commonsense Graph for Object Localisation in Partial Scenes

2022-03-10 · CVPR 2022 1 · Francesco Giuliari, Geri Skenderi, Marco Cristani, Yiming Wang 외

We solve object localisation in partial scenes, a new problem of estimating the unknown position of an object (e.g. where is the bag?) given a partial 3D scan of a scene. The proposed solution is based on a novel scene g…

Graph Neural NetworkObjectPosition

GNN Applied to Ego-nets for Friend Suggestions

2024-12-16 · Evgeny Zamyatin

A major problem of making friend suggestions in social networks is the large size of social graphs, which can have hundreds of millions of people and tens of billions of connections. Classic methods based on heuristics o…

Link Prediction