SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913150503223296 |
|---|---|
| author | Nogueira, Brenda Gonzalez-Montiel, Gisela A. Jiang, Meng Chawla, Nitesh V. Moniz, Nuno |
| author_facet | Nogueira, Brenda Gonzalez-Montiel, Gisela A. Jiang, Meng Chawla, Nitesh V. Moniz, Nuno |
| contents | Molecular property regression struggles with cases in chemically relevant target ranges that are underrepresented in datasets. Standard average error minimization approaches underperform in these highly relevant cases, and oversampling approaches lead to meaningless molecular representations. In this paper, we propose SPECTRA, a spectral, domain-aware graph generation method designed to improve the prediction of underrepresented but relevant molecular property values. It combines a rarity-aware budgeting scheme to focus generation where data are scarce, target-neighbors graph alignment to establish structural correspondence, and interpolation of Laplacian spectra, node features, and targets. Coupled with spectral GNN using edge-aware Chebyshev convolutions, SPECTRA shows its effectiveness in property prediction benchmarks with competitive performance over leading state-of-the-art methods in relevant target ranges, while requiring ~4x less computational time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04838 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression Nogueira, Brenda Gonzalez-Montiel, Gisela A. Jiang, Meng Chawla, Nitesh V. Moniz, Nuno Machine Learning Spectral Theory Molecular Networks Molecular property regression struggles with cases in chemically relevant target ranges that are underrepresented in datasets. Standard average error minimization approaches underperform in these highly relevant cases, and oversampling approaches lead to meaningless molecular representations. In this paper, we propose SPECTRA, a spectral, domain-aware graph generation method designed to improve the prediction of underrepresented but relevant molecular property values. It combines a rarity-aware budgeting scheme to focus generation where data are scarce, target-neighbors graph alignment to establish structural correspondence, and interpolation of Laplacian spectra, node features, and targets. Coupled with spectral GNN using edge-aware Chebyshev convolutions, SPECTRA shows its effectiveness in property prediction benchmarks with competitive performance over leading state-of-the-art methods in relevant target ranges, while requiring ~4x less computational time. |
| title | SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression |
| topic | Machine Learning Spectral Theory Molecular Networks |
| url | https://arxiv.org/abs/2511.04838 |