Explainable graph attention network for stress recognition (StressGAT) via differential action units

• URL: http://arxiv.org/abs/2607.20819v2
• Date: Mon, 27 Jul 2026 01:59:08 GMT
• Title: Explainable graph attention network for stress recognition (StressGAT) via differential action units
• Abstract summary: This study introduces StressGAT, a Graph Attention Network to capture complex facial dynamics that indicate acute stress.<n>The proposed model 88.62% accuracy on a diverse stress-induction cohort (58 participants) using a subject-independent, Leave-One-Subject-Out (LOSO) protocol.
• Score: 0.5350912957086597
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stress is a dynamic process characterized by significant individual variability in facial expression. Traditional architectures, such as Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs), often overlook person-specific baselines or lack the representational capacity to model the non-linear temporal progression of distress due to sequential bottlenecks and rigid grid-based constraints. Furthermore, many deep learning models lack the interpretability required for clinical deployment. This study introduces StressGAT, a Graph Attention Network that leverages the relational inductive bias of graph modeling to capture complex facial dynamics that indicate acute stress. By using Differential Action Units, the framework normalizes individual responses relative to neutral baselines to achieve personalized recognition. The proposed model achieves 88.62\% accuracy on a diverse stress-induction cohort (58 participants) using a subject-independent, Leave-One-Subject-Out (LOSO) cross-validation protocol. Beyond predictive accuracy, the architecture integrates a Multiple Instance Learning (MIL) attention mechanism to identify peak stress intervals and reveal distinct expressivity phenotypes. By simultaneously optimizing for accuracy and interpretability, this framework provides a robust, explainable solution for personalized affective monitoring.

Related papers

• Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction [10.55782327097476]
  This paper proposes the Structure-Guided Stemporal Attention Graph Neural Network (SGSAN) for traffic prediction.<n>We show that SGSAN achieves state-of-the-art predictive accuracy while providing built-in interpretability that organically aligns with traffic network logic.
  arXiv  Detail & Related papers  (2026-08-14T10:46:37Z)
• Synheart Capacity: A Theory-Driven Physiological Representation of Cognitive Capacity Dynamics from Wearable Signals [0.0]
  We propose a theory-driven framework that models capacity-related cognitive state as a two-dimensional physiological representation.<n>The proposed architecture combines dual-stream encoding of cardiac (IBI/HRV) and electrodermal (EDA) signals with late fusion and task-specific output heads.<n>We show that the proposed effort--stress state-space enables structured differentiation between distinct cognitive regimes.
  arXiv  Detail & Related papers  (2026-05-23T05:58:56Z)
• FIGNN: Feature-Specific Interpretability for Graph Neural Network Surrogate Models [0.0]
  This work presents a novel graph neural network architecture, the Feature-specific Interpretable Graph Neural Network (FIGNN)<n>FIGNN is designed to enhance the interpretability of deep learning surrogate models defined on unstructured grids in scientific applications.
  arXiv  Detail & Related papers  (2025-06-13T01:45:37Z)
• Decoding the Stressed Brain with Geometric Machine Learning [3.8982812950782253]
  Stress contributes to both mental and physical disorders.<n>In this study, we introduce a novel framework that employs geometric machine learning to detect stress from raw recordings.
  arXiv  Detail & Related papers  (2025-05-31T14:47:48Z)
• Personalization of Stress Mobile Sensing using Self-Supervised Learning [1.7598252755538808]
  Stress is widely recognized as a major contributor to a variety of health issues. Real-time stress prediction can enable digital interventions to immediately react at the onset of stress, helping to avoid many psychological and physiological symptoms such as heart rhythm irregularities. However, major challenges with the prediction of stress using machine learning include the subjectivity and sparseness of the labels, a large feature space, relatively few labels, and a complex nonlinear and subjective relationship between the features and outcomes.
  arXiv  Detail & Related papers  (2023-08-04T22:26:33Z)
• Bayesian Networks for the robust and unbiased prediction of depression and its symptoms utilizing speech and multimodal data [65.28160163774274]
  We apply a Bayesian framework to capture the relationships between depression, depression symptoms, and features derived from speech, facial expression and cognitive game data collected at thymia.
  arXiv  Detail & Related papers  (2022-11-09T14:48:13Z)
• Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification [69.45543438974963]
  We find graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues. The well-trained input features weaken the learning of graph topology, making it not generalized enough during the inference process. We propose a Counterfactual Intervention Feature Transfer (CIFT) method to tackle these problems.
  arXiv  Detail & Related papers  (2022-08-01T16:15:31Z)
• Brain dynamics via Cumulative Auto-Regressive Self-Attention [0.0]
  We present a model that is considerably shallow than deep graph neural networks (GNNs) Our model learns the autoregressive structure of individual time series and estimates directed connectivity graphs. We demonstrate our results on a functional neuroimaging dataset classifying schizophrenia patients and controls.
  arXiv  Detail & Related papers  (2021-11-01T21:50:35Z)
• Interpretable Social Anchors for Human Trajectory Forecasting in Crowds [84.20437268671733]
  We propose a neural network-based system to predict human trajectory in crowds. We learn interpretable rule-based intents, and then utilise the expressibility of neural networks to model scene-specific residual. Our architecture is tested on the interaction-centric benchmark TrajNet++.
  arXiv  Detail & Related papers  (2021-05-07T09:22:34Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.