Institution profile

Wageningen University & Research

Academic institutioneurope · nl
Official website
Research library77linked papers
Opportunities0open roles
Selected work

Representative Papers

Solving partial differential equations with sampled neural networks

May 31, 2024arXiv.org

To address the gradient optimization difficulties and non-causal temporal treatment inherent in physics-informed neural networks (PINNs) for time-dependent partial differential equations (PDEs), this work proposes a gradient-free, causally structured stochastic neural basis function method. Spatially, it constructs neural basis functions with random weights in the hidden layer; temporally, it explicitly integrates time evolution via classical ODE solvers. We introduce a novel dual-mode weight sampling strategy—data-agnostic and data-aware—and establish its $L^2$ convergence in Barron space theoretically. The method combines mesh-free flexibility with spectral convergence accuracy. It enables long-time-domain simulation and inverse problem solving. Numerical experiments across diverse elliptic and time-dependent PDEs demonstrate 1–2 orders-of-magnitude improvements in training speed and accuracy over PINNs, alongside strong generalization capability and numerical stability.

5 citationsRead paper

Inductive Graph Layout with Implicit Neural Fields

Aug 09, 2026

This work proposes a novel approach to graph layout by introducing implicit neural fields, departing from traditional methods that rely on explicit coordinate optimization and suffer from high computational complexity and poor generalization to unseen nodes. The method models the mapping from node features to coordinates as a learnable function, enabling efficient fitting of layout energy using only a small set of anchor points. It supports inductive inference, stochastic stress variants, and multi-objective aesthetic optimization, while leveraging a lightweight neural network and low-rank approximation for fast inference. Experiments demonstrate superior performance over PivotMDS, landmark MDS, and kernel ridge regression in layout energy approximation, with the ability to generalize to the entire graph in a single forward pass, substantially reducing computational overhead.

0 citationsRead paper
Recent publications

Latest Papers

Inductive Graph Layout with Implicit Neural Fields

Aug 09, 2026

This work proposes a novel approach to graph layout by introducing implicit neural fields, departing from traditional methods that rely on explicit coordinate optimization and suffer from high computational complexity and poor generalization to unseen nodes. The method models the mapping from node features to coordinates as a learnable function, enabling efficient fitting of layout energy using only a small set of anchor points. It supports inductive inference, stochastic stress variants, and multi-objective aesthetic optimization, while leveraging a lightweight neural network and low-rank approximation for fast inference. Experiments demonstrate superior performance over PivotMDS, landmark MDS, and kernel ridge regression in layout energy approximation, with the ability to generalize to the entire graph in a single forward pass, substantially reducing computational overhead.

0 citationsRead paper

HugSelect: An Explainable Multi-Criteria Decision-Support Framework for foundation-model selection

Aug 08, 2026

This work addresses the lack of systematic, auditable decision support in foundational model selection, a process often driven by popularity rather than functional capabilities, operational constraints, or community-based quality assessments. To remedy this, we propose HugSelect—the first interpretable multi-criteria decision framework that formalizes foundational model selection as a traceable software component selection task. HugSelect integrates model metadata, functional attributes, and community-perceived quality into a unified knowledge base and a decomposable weighted scoring system. Evaluated on 71,274 models, our approach achieves an F1 score of 0.801 in functional feature extraction and 0.84 accuracy in quality mapping. It attains model-level Coverage@10 of 0.61 and family-level Coverage@10 of 0.91, matching the recommendation performance of leading commercial systems while offering transparent, interpretable results that elicit positive user feedback.

0 citationsRead paper