Simple GNNs with Low Rank Non-parametric Aggregators
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913586686722048 |
|---|---|
| author | Vinas, Luciano Amini, Arash A. |
| author_facet | Vinas, Luciano Amini, Arash A. |
| contents | We revisit recent spectral GNN approaches to semi-supervised node classification (SSNC). We posit that state-of-the-art (SOTA) GNN architectures may be over-engineered for common SSNC benchmark datasets (citation networks, page-page networks, etc.). By replacing feature aggregation with a non-parametric learner we are able to streamline the GNN design process and avoid many of the engineering complexities associated with SOTA hyperparameter selection (GNN depth, non-linearity choice, feature dropout probability, etc.). Our empirical experiments suggest conventional methods such as non-parametric regression are well suited for semi-supervised learning on sparse, directed networks and a variety of other graph types commonly found in SSNC benchmarks. Additionally, we bring attention to recent changes in evaluation conventions for SSNC benchmarking and how this may have partially contributed to rising performances over time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_05250 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Simple GNNs with Low Rank Non-parametric Aggregators Vinas, Luciano Amini, Arash A. Machine Learning We revisit recent spectral GNN approaches to semi-supervised node classification (SSNC). We posit that state-of-the-art (SOTA) GNN architectures may be over-engineered for common SSNC benchmark datasets (citation networks, page-page networks, etc.). By replacing feature aggregation with a non-parametric learner we are able to streamline the GNN design process and avoid many of the engineering complexities associated with SOTA hyperparameter selection (GNN depth, non-linearity choice, feature dropout probability, etc.). Our empirical experiments suggest conventional methods such as non-parametric regression are well suited for semi-supervised learning on sparse, directed networks and a variety of other graph types commonly found in SSNC benchmarks. Additionally, we bring attention to recent changes in evaluation conventions for SSNC benchmarking and how this may have partially contributed to rising performances over time. |
| title | Simple GNNs with Low Rank Non-parametric Aggregators |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2310.05250 |