# Node Classification on AmazonPhoto largest connected component (LCC) (Balanced)

Source: [Node Classification on AmazonPhoto largest connected component (LCC) (Balanced)](<https://www.sota2.com/research/sota/node-classification-on-amazonphoto-largest-connected-component-lcc-balanced>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:27:43.354Z

Evaluation of Node Classification performance on the Balanced Largest Connected Component (LCC) subset of the AmazonPhoto graph dataset.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Node classification |
| Dataset (including any stated split) | AmazonPhoto largest connected component (LCC) (Balanced) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/node-classification-on-amazonphoto-largest-connected-component-lcc-balanced.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GS-mean | 91.4 | Not recorded | 68fa68551e209131cea1b8e9 |
| GIC | 89 | Not recorded | 68fa68551e209131cea1b8e9 |
| DGI | 86.8 | Not recorded | 68fa68551e209131cea1b8e9 |
| GAT | 85.7 | Not recorded | 68fa68551e209131cea1b8e9 |

### GS-mean

Accuracy: 91.4. Result ID: 698d6b378b517eb433215bfe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68551e209131cea1b8e9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c31e209131cea0664e.md>)

[Implementation](<http://snap.stanford.edu/graphsage/>)

Recorded evaluation configuration: {"Learning Paradigm":"Semi-supervised"}. This record does not assert independent reproduction.

### GIC

Accuracy: 89. Result ID: 698d6b378b517eb433215bfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68551e209131cea1b8e9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68551e209131cea1b8e9.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction.

### DGI

Accuracy: 86.8. Result ID: 698d6b378b517eb433215bfd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68551e209131cea1b8e9.md>)

Recorded evaluation configuration: {"Learning Paradigm":"Unsupervised"}. This record does not assert independent reproduction.

### GAT

Accuracy: 85.7. Result ID: 698d6b378b517eb433215bff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68551e209131cea1b8e9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640b1e209131cea0244e.md>)

[Implementation](<https://github.com/PetarV-/GAT>)

Recorded evaluation configuration: {"Learning Paradigm":"Semi-supervised"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.