Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Few-shot Node Classification with Extremely Weak Supervision

About

Few-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i.e., meta-training classes) and then generalize to classes with limited labeled nodes (i.e., meta-test classes). Nevertheless, on real-world graphs, it is usually difficult to obtain abundant labeled nodes for many classes. In practice, each meta-training class can only consist of several labeled nodes, known as the extremely weak supervision problem. In few-shot node classification, with extremely limited labeled nodes for meta-training, the generalization gap between meta-training and meta-test will become larger and thus lead to suboptimal performance. To tackle this issue, we study a novel problem of few-shot node classification with extremely weak supervision and propose a principled framework X-FNC under the prevalent meta-learning framework. Specifically, our goal is to accumulate meta-knowledge across different meta-training tasks with extremely weak supervision and generalize such knowledge to meta-test tasks. To address the challenges resulting from extremely scarce labeled nodes, we propose two essential modules to obtain pseudo-labeled nodes as extra references and effectively learn from extremely limited supervision information. We further conduct extensive experiments on four node classification datasets with extremely weak supervision to validate the superiority of our framework compared to the state-of-the-art baselines.

Song Wang, Yushun Dong, Kaize Ding, Chen Chen, Jundong Li• 2023

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy82.7
583
Node ClassificationCiteseer
Accuracy70.29
503
Node ClassificationCora-ML
Accuracy90.36
326
Node ClassificationOgbn-arxiv
Accuracy63.19
304
few-shot node classificationCoraFull
Accuracy71.26
68
few-shot node classificationCoauther CS
Accuracy92.03
68
Node ClassificationCoraFull 5-way 3-shot (test)
Accuracy69.32
36
Node ClassificationCoauthor-CS 5 way 3 shot
Accuracy82.93
20
Node ClassificationCoauthor-CS 5 way 5 shot
Accuracy84.36
20
Node ClassificationCora 2 way 3 shot
Accuracy (%)78.19
20
Showing 10 of 18 rows

Other info

Follow for update