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

Deep Insights into Noisy Pseudo Labeling on Graph Data

About

Pseudo labeling (PL) is a wide-applied strategy to enlarge the labeled dataset by self-annotating the potential samples during the training process. Several works have shown that it can improve the graph learning model performance in general. However, we notice that the incorrect labels can be fatal to the graph training process. Inappropriate PL may result in the performance degrading, especially on graph data where the noise can propagate. Surprisingly, the corresponding error is seldom theoretically analyzed in the literature. In this paper, we aim to give deep insights of PL on graph learning models. We first present the error analysis of PL strategy by showing that the error is bounded by the confidence of PL threshold and consistency of multi-view prediction. Then, we theoretically illustrate the effect of PL on convergence property. Based on the analysis, we propose a cautious pseudo labeling methodology in which we pseudo label the samples with highest confidence and multi-view consistency. Finally, extensive experiments demonstrate that the proposed strategy improves graph learning process and outperforms other PL strategies on link prediction and node classification tasks.

Botao Wang, Jia Li, Yang Liu, Jiashun Cheng, Yu Rong, Wenjia Wang, Fugee Tsung• 2023

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy84.62
1215
Node ClassificationPubmed
Accuracy80.62
627
Node ClassificationCiteseer
Accuracy74.22
503
Node ClassificationAmazon Photo
Accuracy93.72
313
Link PredictionCiteseer
AUC72.45
162
Node ClassificationLastFMAsia
Accuracy83.56
16
Link PredictionwikiCS
AUC95.56
13
Link PredictionActor
AUC73.54
13
Link PredictionTwitchPT
AUC87.87
6
Link PredictionAmazon Photo
AUC89.53
6
Showing 10 of 10 rows

Other info

Follow for update