← Back to all news
arXiv Machine Learning By Kareem M. Gameel, Ihor Neporozhnii, Sjoerd Hoogland, Oleksandr Voznyy

The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning

Read the original on arXiv Machine Learning →

The paper investigates the effectiveness of Δ-learning in scientific machine learning, showing that simply reducing residual error magnitude does not guarantee easier learning. By testing molecular graph neural networks on total energy predictions, the authors find that complex local descriptor baselines can produce small residuals that are actually rougher and harder to learn, whereas a semi‑empirical baseline both shrinks the residual scale and smooths the target space. They propose a new diagnostic, scale‑normalized graph Dirichlet roughness (SD_{R}), to assess residual learnability and argue that choosing complementary baselines is as important as model architecture for successful target design.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jun 3

GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond

arXiv:2606. 03232v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have revolutionized Neural Force Fields for atomistic simulations, achieving near-quantum accuracy at reduced cost, yet adapting these models to new chemical systems requires expensive retraining of foundation models.

By Parth Verma, Parv P. Singh, Vipul Garg, Ishita Thakre, N. M. Anoop Krishnan, Sayan Ranu
ragfine-tuningbenchmarkssafety
More like this →
arXiv Machine Learning
Jun 30

Shoot from the HIP: Hessian Interatomic Potentials without derivatives

arXiv:2509. 21624v3 Announce Type: replace Abstract: Fundamental tasks in computational chemistry, from transition state search to vibrational analysis, rely on molecular Hessians, which are the second derivatives of the potential energy.

By Andreas Burger, Luca Thiede, Nikolaj R{\o}nne, Varinia Bernales, Nandita Vijaykumar, Tejs Vegge, Arghya Bhowmik, Alan Aspuru-Guzik
benchmarks
More like this →
arXiv AI
Sep 17

Procedural Pretraining for Molecular Property Prediction

The paper proposes a three‑stage training pipeline that begins with procedural pretraining on abstract, procedurally generated data, followed by molecular pretraining on SMILES, and finally downstream fine‑tuning for molecular property prediction. Experiments show that procedural pretraining improves downstream performance—e.g., a 4.8% error reduction on Lipophilicity—especially when labeled data are scarce, and that the benefit peaks at an intermediate procedural training budget. Analysis indicates that transferable knowledge resides mainly in attention layers, while feed‑forward layers may over‑specialize.

By Moritz Friedemann, Zachary Shinnick, Philip Torr, Bruno Andreis
fine-tuning
More like this →
arXiv Machine Learning
Sep 21

Transformers Discover Molecular Structure Without Graph Priors

The paper investigates whether machine learning models can uncover physical patterns in atomistic data without relying on traditional physics-based inductive biases such as geometric locality or graph structures. By training a general-purpose architecture on molecular simulation data, the authors demonstrate that the model autonomously learns interatomic interaction strengths resembling classical electrostatics and identifies interaction cutoffs aligned with established physical models. The study also reports predictable neural scaling behavior and competitive accuracy on certain metrics compared to physics-informed architectures, suggesting that explicit priors may only be necessary when empirically justified.

By Tobias Kreiman, Yutong Bai, Fadi Atieh, Elizabeth Weaver, Eric Qu, Aditi S. Krishnapriyan
llmssafety
More like this →