Out-of-Support Generalisation via Weight Space Sequence Modelling
arXiv:2602.13550v1 Announce Type: new Abstract: As breakthroughs in deep learning transform key industries, models are increasingly required to extrapolate on datapoints found outside the range of the training set, a challenge we coin as out-of-support (OoS) generalisation. However, neural networks...
Optimization-Free Graph Embedding via Distributional Kernel for Community Detection
arXiv:2602.13634v1 Announce Type: new Abstract: Neighborhood Aggregation Strategy (NAS) is a widely used approach in graph embedding, underpinning both Graph Neural Networks (GNNs) and Weisfeiler-Lehman (WL) methods. However, NAS-based methods are identified to be prone to over-smoothing-the loss of node...
On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling
arXiv:2602.13684v1 Announce Type: new Abstract: Correlation Clustering (CC) is a fundamental unsupervised learning primitive whose strongest LP-based approximation guarantees require $\Theta(n^3)$ triangle inequality constraints and are prohibitive at scale. We initiate the study of \emph{sparsification--approximation trade-offs} for CC, asking how...
Data-driven Bi-level Optimization of Thermal Power Systems with embedded Artificial Neural Networks
arXiv:2602.13746v1 Announce Type: new Abstract: Industrial thermal power systems have coupled performance variables with hierarchical order of importance, making their simultaneous optimization computationally challenging or infeasible. This barrier limits the integrated and computationally scaleable operation optimization of industrial thermal power...
MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction
arXiv:2602.13791v1 Announce Type: new Abstract: Predicting transcriptional responses to unseen genetic perturbations is essential for understanding gene regulation and prioritizing large-scale perturbation experiments. Existing approaches either rely on static, potentially incomplete knowledge graphs, or prompt language models for functionally similar...
Sufficient Conditions for Stability of Minimum-Norm Interpolating Deep ReLU Networks
arXiv:2602.13910v1 Announce Type: new Abstract: Algorithmic stability is a classical framework for analyzing the generalization error of learning algorithms. It predicts that an algorithm has small generalization error if it is insensitive to small perturbations in the training set such...
GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
arXiv:2602.13921v1 Announce Type: new Abstract: Repository-level bug localization-the task of identifying where code must be modified to fix a bug-is a critical software engineering challenge. Standard Large Language Modles (LLMs) are often unsuitable for this task due to context window...
Assessing States’ Obligations under the UN Guiding Principles on Business and Human Rights Post-Brexit
Private economic actors wield unprecedented influence over the enjoyment of human rights, yet legal systems remain uneven in their regulation of corporate responsibility. Against this backdrop, this article examines a largely underexplored post-Brexit trajectory, the regulatory divergence in the implementation...
Review of Hanna Schebesta and Kai Purnhagen, EU Food Law, Oxford, Oxford University Press, 2024, 432 pp, hb, £110.00
Anyone interested in food system reform should acknowledge the importance of EU law and learn to recognise its strengths and weaknesses, so as to fully harness its transformative potential. This is no easy task, for EU food law is a...