arXiv subjects

Vân Anh Huynh-Thu

Publications and source records attributed to Vân Anh Huynh-Thu.

6 recordsLinked to original sources

arXiv2026

Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence

Over the last few years, there has been an increased interest in making machine learning models more interpretable. Although a great deal of effort goes into developing techniques for interpreting the interactions learned by a given model, fewer studies focus on assessing the quality of such explanations. Even fewer focus on how to adjust the model to produce explanations faithful to prior knowledge, a process known as explanation-guided learning. Furthermore, most approaches in this area focus on classification problems and usually assume prior knowledge about which input features or regions are most important. In this work, we introduce a new approach to steering neural networks based on partial dependence, such that their average response to certain features aligns with specific functional domain knowledge about the problem. We empirically demonstrate on a range of regression problems, including dynamical systems forecasting, that models whose training has been controlled using our method perform better than unconstrained models and are more data-efficient. Moreover, we highlight that interpretations obtained from the former actually align with the user-provided knowledge, whereas those obtained from the latter do not.

cs.LG↗

arXiv2025

Hybrid additive modeling with partial dependence for supervised regression and dynamical systems forecasting

Learning processes by exploiting restricted domain knowledge is an important task across a plethora of scientific areas, with more and more hybrid training methods additively combining data-driven and model-based approaches. Although the obtained models are more accurate than purely data-driven models, the optimization process usually comes with sensitive regularization constraints. Furthermore, while such hybrid methods have been tested in various scientific applications, they have been mostly tested on dynamical systems, with only limited study about the influence of each model component on global performance and parameter identification. In this work, we introduce a new hybrid training approach based on partial dependence, which removes the need for intricate regularization. Moreover, we assess the performance of hybrid modeling against traditional machine learning methods on standard regression problems. We compare, on both synthetic and real regression problems, several approaches for training such hybrid models. We focus on hybrid methods that additively combine a parametric term with a machine learning term and investigate model-agnostic training procedures. Therefore, experiments are carried out with different types of machine learning models, including tree-based models and artificial neural networks. We also extend our partial dependence optimization process for dynamical systems forecasting and compare it to existing schemes.

cs.LG↗

arXiv2023

Optimizing model-agnostic Random Subspace ensembles

This paper presents a model-agnostic ensemble approach for supervised learning. The proposed approach is based on a parametric version of Random Subspace, in which each base model is learned from a feature subset sampled according to a Bernoulli distribution. Parameter optimization is performed using gradient descent and is rendered tractable by using an importance sampling approach that circumvents frequent re-training of the base models after each gradient descent step. The degree of randomization in our parametric Random Subspace is thus automatically tuned through the optimization of the feature selection probabilities. This is an advantage over the standard Random Subspace approach, where the degree of randomization is controlled by a hyper-parameter. Furthermore, the optimized feature selection probabilities can be interpreted as feature importance scores. Our algorithm can also easily incorporate any differentiable regularization term to impose constraints on these importance scores.

cs.LG↗

arXiv2018

Gene regulatory network inference: an introductory survey

Gene regulatory networks are powerful abstractions of biological systems. Since the advent of high-throughput measurement technologies in biology in the late 90s, reconstructing the structure of such networks has been a central computational problem in systems biology. While the problem is certainly not solved in its entirety, considerable progress has been made in the last two decades, with mature tools now available. This chapter aims to provide an introduction to the basic concepts underpinning network inference tools, attempting a categorisation which highlights commonalities and relative strengths. While the chapter is meant to be self-contained, the material presented should provide a useful background to the later, more specialised chapters of this book.

q-bio.QM↗

arXiv2016

Context-dependent feature analysis with random forests

In many cases, feature selection is often more complicated than identifying a single subset of input variables that would together explain the output. There may be interactions that depend on contextual information, i.e., variables that reveal to be relevant only in some specific circumstances. In this setting, the contribution of this paper is to extend the random forest variable importances framework in order (i) to identify variables whose relevance is context-dependent and (ii) to characterize as precisely as possible the effect of contextual information on these variables. The usage and the relevance of our framework for highlighting context-dependent variables is illustrated on both artificial and real datasets.

stat.ML↗

arXiv2014

Bridging physiological and evolutionary time scales in a gene regulatory network

Gene regulatory networks (GRN) govern phenotypic adaptations and reflect the trade-offs between physiological responses and evolutionary adaptation that act at different time scales. To identify patterns of molecular function and genetic diversity in GRNs, we studied the drought response of the common sunflower, Helianthus annuus, and how the underlying GRN is related to its evolution. We examined the responses of 32,423 expressed sequences to drought and to abscisic acid and selected 145 co-expressed transcripts. We characterized their regulatory relationships in nine kinetic studies based on different hormones. From this, we inferred a GRN by meta-analyses of a Gaussian graphical model and a random forest algorithm and studied the genetic differentiation among populations (FST) at nodes. We identified two main hubs in the network that transport nitrate in guard cells. This suggests that nitrate transport is a critical aspect of sunflower physiological response to drought. We observed that differentiation of the network genes in elite sunflower cultivars is correlated with their position and connectivity. This systems biology approach combined molecular data at different time scales and identified important physiological processes. At the evolutionary level, we propose that network topology could influence responses to human selection and possibly adaptation to dry environments.

q-bio.MN↗