Bayesian Evidence Accumulation for Graph-Based Learning in Dynamic Data-Driven Applications Systems

Moises Ponce; Sarah Harkins Dayton; Ioannis Schizas; Vasileios Maroulas

cs.LGOct 26, 2026

Bayesian Evidence Accumulation for Graph-Based Learning in Dynamic Data-Driven Applications Systems

Authors: Moises Ponce, Sarah Harkins Dayton, Ioannis Schizas, Vasileios Maroulas

Organizations: University of Tennessee, Knoxville TN 37996, USA · US Army Combat Capabilities Development Command, Army Research Laboratory, Adelphi MD 20783, USA

Abstract

Graph Neural Networks (GNNs) are widely used in modern machine learning, yet most existing frameworks remain fundamentally static, limiting their applicability in Dynamic Data Driven Application Systems (DDDAS) where observations arrive sequentially under uncertainty. We introduce B-EAGLe (Bayesian Evidence Accumulation for Graph-Based Learning), a probabilistic framework inspired by CBGT-Net (cortico-basal ganglia-thalamic network) that reformulates graph classification as a sequential evidence accumulation process. B-EAGLe combines a GNN encoder with a Bayesian accumulator that incrementally updates posterior beliefs over class labels as new observations arrive, committing to a decision only when sufficient confidence is achieved. Experiments on CIFAR10 demonstrate competitive performance together with principled confidence estimation under sequential observations.

Figures & tables

Figure 1: Overview of the B-EAGLe computational model illustrating the sequential evidence accumulation pipeline. The dashed border denotes the iterative loop that repeats until the decision variable $d_{t}=1$ or $T_{\max}$ is reached.

Hyperparameter	MNIST-SP	CIFAR10-SP	PATTERN	CLUSTER
# GAT Layers	6	5	12	12
# $L$ -hops	3	3	1	1
Edge Features	True	True	True	False
Dropout	0.15	0.05	0.05	0.1
Hidden Dim	60	65	90	90
Graph Pooling	mean	mean	readout	readout

Table 1: Hyperparameter settings of B-EAGLe following [ 10 ] .

Dataset	Best Baseline	Baseline Acc.	B-EAGLe	Avg. $t_{d}$	Timeout
MNIST-SP	GatedGCN+	$98.71\pm 0.137$	$98.22\pm 0.18$	$11.0\pm 0.16$	0.4%
CIFAR10-SP	GatedGCN+	$77.22\pm 0.381$	$90.13\pm 2.75$	$26.6\pm 0.33$	1.6%
PATTERN	GRIT	$87.20\pm 0.076$	$94.00\pm 4.39$	$50.98\pm 0.01$	100%
CLUSTER	GRIT	$80.03\pm 0.277$	$82.34\pm 0.11$	$50.85\pm 0.05$	98.6%

Table 2: Classification accuracy (%) of B-EAGLe compared against state-of-the-art baselines from [ 10 ] . The average number of observations acquired before committing to a decision is included. The Timeout rate denotes the fraction of episodes requiring all

T_{\max}

observations. Highlighted in green are the best results per dataset.

Graph Classification

Graph classification assigns labels to whole graphs, using their connectivity, node and edge attributes, and learned representations.

See all 37 papers

Online Bayesian Node Classification on Inductive Graphs under Distribution Shift
Sep 12, 2026Jinwen Xu, Gonzalo Mateos Buckstein, Qin LuNode Classification Graph Neural Networks
School of Electrical and Computer Engineering, University of Georgia, Athens, GA, USA · Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA
PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs
Jun 22, 2026Guoguo Ai, Chaoxi Niu, Hui Yan +3Continual Test-Time Adaptation Dynamic Graph Learning
School of Computer Science and Engineering, Nanjing University of Science and Technology, China · School of Computing and Information Systems, Singapore Management University, Singapore · Faculty of Data Science, City University of Macau, Macau, China +3
Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow
Mar 27, 2026Jicheng Ma, Yunyan Yang, Juan Zhao +1Graph Representation Learning Graph Neural Networks
School of Mathematics, Renmin University of China, Beijing, China. · School of Mathematical Sciences, Key Laboratory of Mathematics and Complex Systems of MOE, Beijing Normal University, Beijing, China.

Sep 12, 2026J/K move · Enter open · S save

Online Bayesian Node Classification on Inductive Graphs under Distribution Shift

Jinwen Xu, Gonzalo Mateos Buckstein, Qin Lu

School of Electrical and Computer Engineering, University of Georgia, Athens, GA, USA · Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA

Node Classification Graph Neural Networks Bayesian Neural Networks

Open paper AskPDF arXiv

On evolving graphs, node classifiers must satisfy two key requirements: inductive generalization to newly arriving nodes under distribution shift and calibrated uncertainty for safety-sensitive applications. Standard graph neural networks (GNNs) are typically trained once and address neither requirement. We adapt the Bayesian last-layer (BLL) model by placing random last-layer parameters on top of a deterministic GNN encoder for uncertainty quantification. The categorical softmax likelihood required for classification breaks Gaussian conjugacy, so neither the training posterior nor the test-time streaming update has a closed-form solution. To address both challenges, we introduce a variational Bayesian last-layer (VBLL) objective that jointly trains the encoder and an approximate last-layer posterior by maximizing an evidence lower bound with a Monte Carlo expected log-likelihood. At test time, we freeze the encoder and apply an online Laplace update to the last-layer posterior. This update corresponds to a power-prior Bayesian model with exponential forgetting and a Kullback-Leibler anchor to the training posterior. Across five node-classification benchmarks under distribution shift, online GVBLL is the only method to achieve the best accuracy and negative log-likelihood on every dataset. It improves accuracy by up to 17 percentage points on Cora and 14 percentage points on ogbn-arxiv over the strongest non-GVBLL baseline, while remaining competitive in calibration with MC Dropout, Deep Ensembles, Temperature Scaling, and Gaussian-process classifiers.

Abstract

Graph Classification

Explore similar work

Online Bayesian Node Classification on Inductive Graphs under Distribution Shift

PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs

Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow