# BoGrape: Bayesian optimization over graphs with shortest-path encoded

arXiv: https://arxiv.org/abs/2503.05642 · HTML: https://mlsanity.com/paper/2503.05642/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2025.

## Built on by (most cited first, 7 of 7)

- [The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning](https://mlsanity.com/paper/2506.07619/) (2025)
- [Global optimization of graph acquisition functions for neural architecture search](https://mlsanity.com/paper/2505.23640/) (2025)
- [Global Optimization on Graph-Structured Data via Gaussian Processes with Spectral Representations](https://mlsanity.com/paper/2511.07734/) (2025)
- [Informing Acquisition Functions via Foundation Models for Molecular Discovery](https://mlsanity.com/paper/2512.13935/) (2025)
- [Meta-learning for sample-efficient Bayesian optimisation of fed-batch processes](https://mlsanity.com/paper/2605.05382/) (2026)
- [How Many Initial Points Does Bayesian Optimization Need?](https://mlsanity.com/paper/2607.04356/) (2026)
- [Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering](https://mlsanity.com/paper/2610.02014/) (2026)

## Abstract (arXiv)

Graph-structured data are central to many scientific and industrial applications where the goal is to optimize expensive black-box objectives defined over graph structures or node configurations -- as seen in molecular design, supply chains, and sensor placement. Bayesian optimization offers a principled approach for such settings, but existing methods largely focus on functions defined over nodes of a fixed graph. Moreover, graph optimization is often approached heuristically, and it remains unclear how to systematically incorporate structural constraints into BO. To address these gaps, we build on shortest-path graph kernels to develop a principled framework for acquisition optimization over unseen graph structures and associated node attributes. Through a novel formulation based on mixed-integer programming, we enable global exploration of the combinatorial domain over graph structures and explicit embedding of problem-specific constraints. We demonstrate that our method, BoGrape, is competitive both on general synthetic benchmarks and representative molecular design case studies with application-specific constraints.