Toward Robust Graph Semi-Supervised Learning Against Extreme Data Scarcity
The success of graph neural networks (GNNs) in graph-based web mining highly relies on abundant human-annotated data, which is laborious to obtain in practice. When only a few labeled nodes are available, how to improve their robustness is key to achieving replicable and sustainable graph semi-supervised learning. Though self-training is powerful for semi-supervised learning, its application on graph-structured data may fail because 1) larger receptive fields are not leveraged to capture long-range node interactions, which exacerbates the difficulty of propagating feature-label patterns from labeled nodes to unlabeled nodes and 2) limited labeled data makes it challenging to learn well-separated decision boundaries for different node classes without explicitly capturing the underlying semantic structure. To address the challenges of capturing informative structural and semantic knowledge, we propose a new graph data augmentation framework, augmented graph self-training (AGST), which is built with two new (i.e., structural and semantic) augmentation modules on top of a decoupled GST backbone. In this work, we investigate whether this novel framework can learn a robust graph predictive model under the low-data context. We conduct comprehensive evaluations on semi-supervised node classification under different scenarios of limited labeled-node data. The experimental results demonstrate the unique contributions of the novel data augmentation framework for node classification with few labeled data.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:PP |
|---|---|
| Enthalten in: |
IEEE transactions on neural networks and learning systems - PP(2024) vom: 29. Feb. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Ding, Kaize [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 01.03.2024 published: Print-Electronic Citation Status Publisher |
|---|
| doi: |
10.1109/TNNLS.2024.3351938 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369117638 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369117638 | ||
| 003 | DE-627 | ||
| 005 | 20240301233039.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240301s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TNNLS.2024.3351938 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1313.xml |
| 035 | |a (DE-627)NLM369117638 | ||
| 035 | |a (NLM)38421848 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Ding, Kaize |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Toward Robust Graph Semi-Supervised Learning Against Extreme Data Scarcity |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 01.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status Publisher | ||
| 520 | |a The success of graph neural networks (GNNs) in graph-based web mining highly relies on abundant human-annotated data, which is laborious to obtain in practice. When only a few labeled nodes are available, how to improve their robustness is key to achieving replicable and sustainable graph semi-supervised learning. Though self-training is powerful for semi-supervised learning, its application on graph-structured data may fail because 1) larger receptive fields are not leveraged to capture long-range node interactions, which exacerbates the difficulty of propagating feature-label patterns from labeled nodes to unlabeled nodes and 2) limited labeled data makes it challenging to learn well-separated decision boundaries for different node classes without explicitly capturing the underlying semantic structure. To address the challenges of capturing informative structural and semantic knowledge, we propose a new graph data augmentation framework, augmented graph self-training (AGST), which is built with two new (i.e., structural and semantic) augmentation modules on top of a decoupled GST backbone. In this work, we investigate whether this novel framework can learn a robust graph predictive model under the low-data context. We conduct comprehensive evaluations on semi-supervised node classification under different scenarios of limited labeled-node data. The experimental results demonstrate the unique contributions of the novel data augmentation framework for node classification with few labeled data | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Nouri, Elnaz |e verfasserin |4 aut | |
| 700 | 1 | |a Zheng, Guoqing |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Huan |e verfasserin |4 aut | |
| 700 | 1 | |a White, Ryen |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on neural networks and learning systems |d 2012 |g PP(2024) vom: 29. Feb. |w (DE-627)NLM23236897X |x 2162-2388 |7 nnns |
| 773 | 1 | 8 | |g volume:PP |g year:2024 |g day:29 |g month:02 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TNNLS.2024.3351938 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d PP |j 2024 |b 29 |c 02 | ||