arXiv AI

Rethinking Epistemic Uncertainty in Node Classification through Information Growth

The paper introduces a statistical framework to test whether epistemic uncertainty in node classification decreases as more information about the data‑generating process becomes available. It shows that existing graph evidential deep learning methods fail to meet a consistency criterion under this framework, because they regulate uncertainty via hyperparameters rather than data uncertainty. The authors propose graph bootstrap ensembles, which reduce epistemic uncertainty more effectively than standard deep ensembles and satisfy the consistency criterion in controlled experiments.

arXiv Machine Learning

3d ago

Uncertainty Quantification Is Indispensable for Reliable Connectome-Based Graph Learning: A Narrative Review and Case Study

The paper reviews uncertainty quantification (UQ) methods for graph neural networks used in connectome-based diagnostic classification and presents a case study on a temporal Graph Attention Network applied to dynamic functional connectivity data for Cocaine Use Disorder. It highlights that deterministic GNNs can produce overconfident predictions, as shown by a Monte Carlo dropout audit revealing high confidence on misclassified subjects. The study demonstrates the need for rigorous UQ, calibration, and selective prediction to ensure reliable graph-based biomarkers in clinical neuroscience.

By Mansooreh Pakravan

computer-vision

arXiv AI

Jul 9

Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation

arXiv:2607. 07330v1 Announce Type: cross Abstract: Hypergraph neural networks have shown powerful capability in modeling higher-order relations, yet their predictive uncertainty remains underexplored.

By Zhiheng Zhou, Mengyao Zhou, Dengyi Zhao, Xingqin Qi, Guiying Yan

diffusion benchmarks

arXiv AI

Sep 3

Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion

The paper introduces QUEST, a method for uncertain knowledge graph completion that adds no trainable parameters to the standard pipeline. QUEST first initializes entity embeddings using the smallest non‑trivial eigenvectors of the confidence‑weighted graph Laplacian, thereby preserving community and hub structure before training. It then applies an unbiased mini‑batch Dirichlet energy regularizer to enforce early‑stage structural consistency, leading to improved confidence and link prediction on most metric‑dataset pairs and eliminating instability spikes on dense graphs.

By Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara, Craig A. Knoblock

rag

arXiv Machine Learning

Jun 10

Can we trust our models? Epistemic calibration in second-order classification

arXiv:2606. 10777v1 Announce Type: new Abstract: Uncertainty estimation is critical for deploying machine learning models in high-stakes settings.

By Arthur Hoarau

arXiv Machine Learning

Jun 24

Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning

arXiv:2602. 01477v2 Announce Type: replace-cross Abstract: Evidential Deep Learning (EDL) is a popular framework for uncertainty-aware classification that models predictive uncertainty via Dirichlet distributions parameterized by neural networks.

By Pietro Carlotti, Nevena Gligi\'c, Arya Farahi

safety

arXiv Machine Learning

Jul 17

What Do Temporal Graph Learning Models Learn?

arXiv:2510. 09416v4 Announce Type: replace Abstract: Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models.

By Abigail J. Hayes, Tobias Schumacher, Markus Strohmaier

benchmarks safety

arXiv Machine Learning

Jun 8

Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detection

arXiv:2505. 21285v5 Announce Type: replace Abstract: This work proposes a framework LGKDE that learns kernel density estimation for graphs.

By Xudong Wang, Ziheng Sun, Chris Ding, Jicong Fan

benchmarks

arXiv Machine Learning

3d ago

Uncertainty in Representation Learning on Knowledge Graphs

arXiv:2610.06974v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchm...

By Yuqicheng Zhu

rag benchmarks

arXiv Machine Learning

5d ago

Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation

arXiv:2610.02517v1 Announce Type: new Abstract: Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection an...

By Yu Song, Zhigang Hua, Yan Xie, Bingheng Li, Jingzhe Liu, Bo Long, Jiliang Tang, Hui Liu

rag benchmarks

arXiv AI

Aug 18

GATTA: Graph Active Learning with Test-Time Augmentation

arXiv:2608. 15084v1 Announce Type: cross Abstract: Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision, yet its application to graph-structured data remains largely unexplored.

By Zsombor B\'anfi, Andr\'as G\'ezsi, Andr\'as Formanek

computer-vision

arXiv AI

Jun 16

Visualizing Uncertainty: Spatial Maps of Missing and Conflicting Evidence in Deep Learning

arXiv:2606. 15767v1 Announce Type: cross Abstract: Understanding when and why deep neural networks are uncertain is crucial for deploying reliable machine learning systems in safety-critical domains.

By Dong Hyun Jeong, Feng Chen, Jin-Hee Cho, Lance M. Kaplan, Audun J{\o}sang, Soo-Yeon Ji

benchmarks safety

arXiv Machine Learning

Jul 7

Graph Classification via Network Usable Information: From Representation Evaluation to Structure Selection

arXiv:2607. 03587v1 Announce Type: new Abstract: We propose NetinfoGC, a framework for graph classification that extends the Network Usable Information (NUI) paradigm to graph-level learning.

By Abdullah Shaik, Anwar Said

rag benchmarks

Related stories