Virtual Node Generation for Node Classification in Sparsely-Labeled Graphs

2024-09-12 · Hang Cui, Tarek Abdelzaher

In the broader machine learning literature, data-generation methods demonstrate promising results by generating additional informative training examples via augmenting sparse labels. Such methods are less studied in graphs due to the intricate dependencies among nodes in complex topology structures. This paper presents a novel node generation method that infuses a small set of high-quality synthesized nodes into the graph as additional labeled nodes to optimally expand the propagation of labeled information. By simply infusing additional nodes, the framework is orthogonal to the graph learning and downstream classification techniques, and thus is compatible with most popular graph pre-training (self-supervised learning), semi-supervised learning, and meta-learning methods. The contribution lies in designing the generated node set by solving a novel optimization problem. The optimization places the generated nodes in a manner that: (1) minimizes the classification loss to guarantee training accuracy and (2) maximizes label propagation to low-confidence nodes in the downstream task to ensure high-quality propagation. Theoretically, we show that the above dual optimization maximizes the global confidence of node classification. Our Experiments demonstrate statistically significant performance improvements over 14 baselines on 10 publicly available datasets.

📄 PDF Abstract BibTeX arXiv:2409.07712

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning Meta-Learning Node Classification Self-Supervised Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Virtual Node Tuning for Few-shot Node Classification

2023-06-09 · Zhen Tan, Ruocheng Guo, Kaize Ding, Huan Liu

Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer s…

Classification Graph Representation Learning Meta-Learning Node Classification+1

KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy

2023-11-05 · Qianxiong Xu, Cheng Long, Ziyue Li, Sijie Ruan 외

Sensors are commonly deployed to perceive the environment. However, due to the high cost, sensors are usually sparsely deployed. Kriging is the tailored task to infer the unobserved nodes (without sensors) using the obse…

Graph Classification via Deep Learning with Virtual Nodes

2017-08-14 · Trang Pham, Truyen Tran, Hoa Dam, Svetha Venkatesh

Learning representation for graph classification turns a variable-size graph into a fixed-size vector (or matrix). Such a representation works nicely with algebraic manipulations. Here we introduce a simple method to aug…

Classification Deep Learning General Classification Graph Classification

Revisiting Virtual Nodes in Graph Neural Networks for Link Prediction

2021-09-29 · EunJeong Hwang, Veronika Thost, Shib Sankar Dasgupta, Tengfei Ma

It is well known that the graph classification performance of graph neural networks often improves by adding an artificial virtual node to the graphs, which is connected to all nodes in the graph. Intuitively, the virtua…

Clustering Graph Classification Link Prediction

HopGAT: Hop-aware Supervision Graph Attention Networks for Sparsely Labeled Graphs

2020-04-09 · Chaojie Ji, Ruxin Wang, Rongxiang Zhu, Yunpeng Cai 외

Due to the cost of labeling nodes, classifying a node in a sparsely labeled graph while maintaining the prediction accuracy deserves attention. The key point is how the algorithm learns sufficient information from more n…

General Classification Graph Attention Node Classification