Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter

• URL: http://arxiv.org/abs/2606.12651v1
• Date: Wed, 10 Jun 2026 20:21:56 GMT
• Title: Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter
• Abstract summary: We ask whether cheap, closed-form physical priors, used as auxiliary supervision on a graph neural network (GNN), improve OOD generalization.<n>We add two auxiliary losses to a GINE backbone: a topological complexity regression supervised by the Bertz index, and a strain-energy soft penalty supervised by MMFF94 force-field energy.<n>All three physics-aware variants give a small but statistically significant OOD improvement over the baseline.
• Score: 1.1986159241687198
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine-learning drug-discovery pipelines increasingly rely on generative models that propose molecules far from the data used to train downstream synthesizability filters. Existing filters (SAScore, SCScore, RAscore, DeepSA) are purely statistical and degrade in exactly this out-of-distribution (OOD) regime. We ask whether cheap, closed-form physical priors, used as auxiliary supervision on a graph neural network (GNN), improve OOD generalization. We add two auxiliary losses to a GINE backbone: a topological complexity regression supervised by the Bertz index, and a strain-energy soft penalty supervised by MMFF94 force-field energy. On a 65,177-molecule corpus (HIV, Tox21, COCONUT) labeled by SAScore thresholds we reproduce a strong in-distribution baseline, then evaluate a 4-way ablation (baseline / +complexity / +strain / +both) on a single-source OOD split (train on drug-like HIV+Tox21, test on COCONUT natural products), repeated over 5 seeds with paired bootstrap confidence intervals. All three physics-aware variants give a small but statistically significant OOD improvement over the baseline (mean OOD AUC 0.9774): +complexity Delta = +0.0060 (95% CI [+0.0023, +0.0102]), +strain Delta = +0.0032 ([+0.0008, +0.0052]), +both Delta = +0.0066 ([+0.0038, +0.0093]); every interval excludes zero, and the combination is best. The variants are indistinguishable in-distribution, so the effect is visible only under OOD evaluation. We are explicit that the effects are modest, and we report a cautionary methodological finding: a single-seed version of this experiment produced a qualitatively different (non-monotone) story that did not survive multi-seed evaluation.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• Self-Supervised Pretraining of Molecular Graph Encoders with LeJEPA [0.0]
  Self-supervised pretraining has transformed language and vision, but its value for molecular graph neural networks remains contested.<n>We ask whether pretraining on a large unsupervised corpus improves molecular property prediction.<n>Pretraining improves learned representations but does not robustly improve finetuning.
  arXiv  Detail & Related papers  (2026-09-02T12:08:23Z)
• Inverse Reinforcement Learning for Interpretable Keystroke Biomarkers in Parkinson's Disease [0.0]
  Keystroke dynamics have been explored extensively as a passive digital biomarker for Parkinson's disease (PD)<n>We apply inverse reinforcement learning (IRL) to keystroke data, modeling each keystroke as a discrete choice over typing speed and recovering.<n>To our knowledge this is the first application of IRL to keystroke dynamics.
  arXiv  Detail & Related papers  (2026-06-24T01:11:05Z)
• Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics [0.0]
  Detectors for radio-frequency impairments are usually reported with a single AUC measured on the distribution they were tuned on.<n>We ask whether this optimism can be predicted before any out-of-distribution data is seen.
  arXiv  Detail & Related papers  (2026-06-20T14:10:59Z)
• Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology [0.0]
  We extend our prior finding that untrained CNNs match backpropagation at human V1 by testing the same five learning rules against macaque electrophysiology.<n>The rules are backpropagation (BP), feedback alignment (FA), predictive coding (PC), and spike-timing-dependent plasticity (STDP)<n>Using RSA with identical model weights from our human study, we find: (1) all models achieve higher alignment with macaque early visual cortex (rho = 0.15-0.30 at V1/V2) than with human fMRI (rho = 0.01-0.08); (2) STDP and PC produce the highest macaque V1/V2 alignment
  arXiv  Detail & Related papers  (2026-05-21T12:31:18Z)
• SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting [0.5507813261960522]
  We introduce SpikeProphecy, the first large-scale benchmark for causal, autoregressive spike-count forecasting on real electrophysiology recordings.<n>Our core contribution is a population metric decomposition that separates aggregate performance into temporal fidelity, spatial pattern accuracy, and magnitude-invariant alignment.
  arXiv  Detail & Related papers  (2026-05-13T04:45:35Z)
• Epidemiology of Model Collapse: Modeling Synthetic Data Contamination via Bilayer SIR Dynamics [1.7832408661523071]
  Training on synthetic data causes model collapse, but existing analyses treat this as single-chain degradation.<n>We propose a bilayer coupled SIR/SIRS framework treating data corpora and AI models as two interacting populations.
  arXiv  Detail & Related papers  (2026-04-14T06:49:30Z)
• Identifying Evidence-Based Nudges in Biomedical Literature with Large Language Models [2.2015514798912412]
  We present a scalable, AI-powered system that identifies and extracts evidence-based behavioral nudges from unstructured biomedical literature.<n>Nudges are subtle, non-coercive interventions that influence behavior without limiting choice, showing strong impact on health outcomes like medication adherence.
  arXiv  Detail & Related papers  (2026-02-10T22:36:07Z)
• Intra-tree Column Subsampling Hinders XGBoost Learning of Ratio-like Interactions [0.0]
  We study whether intra-tree column subsampling in XGBoost makes that synthesis harder.<n>Across both processes, intra-tree column subsampling reduces test PR-AUC in the primitives-only setting.<n> Practically, if ratio-like structure is plausible, either avoid intra-tree subsampling or include the intended ratio features.
  arXiv  Detail & Related papers  (2026-01-13T01:27:01Z)
• Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback [50.89125374999765]
  We provide the first convergence guarantee for Optimistic Multiplicative Weights Update ($mathtOMWU$) in NLHF.<n>Our analysis identifies a novel marginal convergence behavior, where the probability of rarely played actions grows exponentially from exponentially small values.
  arXiv  Detail & Related papers  (2025-12-31T12:08:29Z)
• Synaptic Pruning: A Biological Inspiration for Deep Learning Regularization [4.080348897270072]
  We propose a magnitude-based synaptic pruning method that better reflects biology.<n> integrated directly into the training loop as a dropout replacement.<n>Experiments on multiple time series forecasting models including RNN, LSTM, and Patch Time Series Transformer show consistent gains.
  arXiv  Detail & Related papers  (2025-08-12T20:36:00Z)
• Regressor-free Molecule Generation to Support Drug Response Prediction [83.25894107956735]
  Conditional generation based on the target IC50 score can obtain a more effective sampling space. Regressor-free guidance combines a diffusion model's score estimation with a regression controller model's gradient based on number labels.
  arXiv  Detail & Related papers  (2024-05-23T13:22:17Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection [65.67315418971688]
  textttRankFeat is a simple yet effective textttpost hoc approach for OOD detection. textttRankFeat achieves the emphstate-of-the-art performance and reduces the average false positive rate (FPR95) by 17.90% compared with the previous best method.
  arXiv  Detail & Related papers  (2022-09-18T16:01:31Z)
• CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks [51.589769497681175]
  The novel coronavirus (SARS-CoV-2) has led to a pandemic. The current testing regime based on Reverse Transcription-Polymerase Chain Reaction for SARS-CoV-2 has been unable to keep up with testing demands. We propose a framework called CovidDeep that combines efficient DNNs with commercially available WMSs for pervasive testing of the virus.
  arXiv  Detail & Related papers  (2020-07-20T21:47:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.