arXiv:2609.13609v1 Announce Type: cross Abstract: Network analysis for multivariate time series is popular in many fields, from neuroscience to seismology. The inverse spectral density is a common ch...
The paper presents a new method for detecting isolated pixels in both binary and grayscale images by extending a neuron-based anomaly detection model to use contrast-sensitive receptive fields with excitatory and inhibitory regions. It addresses limitations of existing techniques such as template matching and second‑order derivative methods, which are either infeasible for grayscale images or overly sensitive to noise and require user‑defined thresholds. The proposed approach eliminates the need for user‑specified parameters, offering a robust, efficient solution applicable across various image processing domains.
arXiv:2606. 29098v1 Announce Type: cross Abstract: A growing number of techniques leverage the spatial structures that underlie many real-world datasets.
arXiv:2607. 09788v1 Announce Type: cross Abstract: Alzheimer's disease (AD) is a common neurodegenerative disorder, and early diagnosis is of great significance for delaying disease progression and enabling timely intervention.
The paper introduces a multiscale community-based fingerprinting framework for signed functional brain networks, using a signed multilayer community detection approach that captures both correlated and anti-correlated activity. Graph-theoretic metrics derived from the joint community structures yield low-dimensional, interpretable fingerprints that reliably identify individuals across multiple sessions and tasks. Evaluation on 810 healthy controls from the Human Connectome Project demonstrates that these community-based fingerprints outperform traditional edge-level methods in stability and interpretability.
The paper introduces MS‑WDRO, a multi‑source Wasserstein distributionally robust optimization framework for reconstructing complex network topologies from scarce target‑domain data and abundant heterogeneous source data. It fuses sources via a weighted Wasserstein barycenter, builds an ambiguity set around it, and solves a regularized Laplacian estimator using a provably convergent ADMM scheme. The authors provide finite‑sample guarantees, demonstrate that naive aggregation is suboptimal, and show through experiments on synthetic data and the ABIDE I neuroimaging dataset that MS‑WDRO outperforms seven baselines in graph recovery, sample efficiency, and diagnostic utility, especially when target samples are limited.
arXiv:2608. 19914v1 Announce Type: new Abstract: Network topology inference from graph signals is central to graph signal processing with applications in neuroscience, sensor, and social networks.
BrainNet Studio is a unified toolkit that enables the construction, analysis, and visualization of both static and dynamic brain networks. It integrates 27 algorithms—including deep learning, graph neural networks, and spatiotemporal sequence models—to support classification, biomarker identification, and the extraction of discriminative brain regions and connections. The toolkit also employs a large language model to generate researcher‑verifiable summaries of functional and structural connectivity, as well as structure‑function coupling, at individual and group levels.
arXiv:2510. 24043v4 Announce Type: replace Abstract: This paper presents Two-Stage LKPLO, a novel multi-stage outlier detection framework that overcomes the coexisting limitations of conventional projection-based methods: their reliance on a fixed statistical metric and their assumption of a single data structure.
FoundAna is a GNN‑assisted foundation model designed for graph anomaly detection across diverse datasets. It combines a GNN component with a transformer encoder enhanced by four positional encodings to capture both local and global structure, using reconstruction errors as anomaly scores. Experiments on nine benchmark datasets from financial, social, and citation networks show that FoundAna consistently outperforms state‑of‑the‑art baselines.
arXiv:2606. 03322v1 Announce Type: cross Abstract: The graphical representation of the brain offers critical insights into diagnosing and prognosing neurodegenerative disease via relationships between regions of interest (ROIs).
The paper introduces DISCO, a deep‑learning framework for detecting overlapping communities in networks. DISCO integrates a diffusion‑based structural prior, sparse multi‑head attention, and a Bernoulli‑Poisson edge‑reconstruction objective to infer community affiliations from node attributes and structural profiles. Experiments show competitive performance against existing graph convolutional and attention methods, and a cybersecurity proof‑of‑concept demonstrates how community changes can signal anomalies in dynamic communication networks.