Community detection is a longstanding topic in graph and Web algorithms, and semi-supervised local community detection, identifying the community to which the given user belongs, garners increasing research attention in recent years. While achieving encouraging results, existing solutions often encounter accumulated errors due to the weak supervision in the community expansion process, and are undermined by the initial seed sensitivity that a suboptimal or boundary seed node can easily misguide community generation. To fill these gaps, we propose a fresh generative perspective on hyperbolic space, which recasts this problem as the seed-conditioned sequence generation, and reformulates community generation as a continuous transport of probability distributions in the manifold measure space. In this paper, we present a novel Semi-supervised Local community detection framework based on hyperbolic Flow Matching (SLFM). Specifically, it leverages a geometric-aware Seed Selector that refines initial seeds with hyperbolic angular and radial priors, and a Hyperbolic Flow Transporter that learns a vector field to map a source distribution to a target community distribution, generating a robust set of anchors. Finally, a Community Expander is introduced to utilize these anchors as surrogate supervision to effectively recover the full community. Experimental results on four real-world datasets demonstrate that SLFM significantly outperforms existing methods in both local and global semi-supervised settings.

Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show potential in ZSAD but have limitations: relying on manually crafted fixed textual descriptions or anomaly prompts is time-consuming and prone to semantic ambiguity, and CLIP struggles with pixel-level anomaly segmentation, focusing more on global semantics than local details. To address these limitations, We introduce KAnoCLIP, a novel ZSAD framework that leverages vision-language models. KAnoCLIP combines general knowledge from a Large Language Model (GPT-3.5) and fine-grained, image-specific knowledge from a Visual Question Answering system (Llama3) via Knowledge-Driven Prompt Learning (KnPL). KnPL uses a knowledge-driven (KD) loss function to create learnable anomaly prompts, removing the need for fixed text prompts and enhancing generalization. KAnoCLIP includes the CLIP visual encoder with V-V attention (CLIP-VV), Bi-Directional Cross-Attention for Multi-Level Cross-Modal Interaction (Bi-CMCI), and Conv-Adapter. These components preserve local visual semantics, improve local cross-modal fusion, and align global visual features with textual information, enhancing pixel-level anomaly detection. KAnoCLIP achieves state-of-the-art performance in ZSAD across 12 industrial and medical datasets, demonstrating superior generalization compared to existing methods.

Source localization, the inverse problem of information diffusion, shows fundamental importance for understanding social dynamics. While achieving notable progress, existing solutions are typically exposed to the risk of error accumulation, and require a large number of observations for effective inference. However, it is often impractical to obtain quantities of observations in real scenarios, highlighting the need for a transferable model with broad applicability. Recently, Riemannian geometry has demonstrated its effectiveness in information diffusion and offers guidance in knowledge transfer, but has yet to be explored in source localization. In light of the issues above, we propose to study transferable source localization from a fresh geometric perspective, and present a novel approach (Trace) on the Riemannian manifold. Concretely, we establish a structural Schrodinger bridge to directly model the map between source and final distributions, where a functional curvature, encapsulating the graph structure, is formulated to govern the Schrodinger bridge and facilitate domain adaptation. Furthermore, we design a simple yet effective learning algorithm for Riemannian Schrodinger bridges (geodesics bridge matching) in which we prove the optimal projection holds for Riemannian measure so that the expensive iterative procedure is avoided. Extensive experiments demonstrate the effectiveness and transferability of Trace on both synthetic and real datasets.

The foundation model has heralded a new era in artificial intelligence, pretraining a single model to offer cross-domain transferability on different datasets.Graph neural networks excel at learning graph data, the omnipresent non-Euclidean structure, but often lack the generalization capacity.Hence, graph foundation model is drawing increasing attention, and recent efforts have been made to leverage Large Language Models.On the one hand, existing studies primarily focus on text-attributed graphs, while a wider range of real graphs do not contain fruitful textual attributes.On the other hand, the sequential graph description tailored for the Large Language Model neglects the structural complexity, which is a predominant characteristic of the graph.Such limitations motivate an important question: Can we go beyond Large Language Models, and pretrain a universal model to learn the structural knowledge for any graph?The answer in the language or vision domain is a shared vocabulary.We observe the fact that there also exist shared substructures underlying graph domain, and thereby open a new opportunity of graph foundation model with structural vocabulary.The key innovation is the discovery of a simple yet effective structural vocabulary of trees and cycles, and we explore its inherent connection to Riemannian geometry.Herein, we present a universal pretraining model, RiemannGFM.Concretely, we first construct a novel product bundle to incorporate the diverse geometries of the vocabulary.Then, on this constructed space, we stack Riemannian layers where the structural vocabulary, regardless of specific graph, is learned in Riemannian manifold offering cross-domain transferability.Extensive experiments show the effectiveness of RiemannGFM on a diversity of real graphs.

The heat-electric-integrated energy system (HE-IES) represents a prominent approach to achieving low-carbon energy supply, garnering considerable attention from both theoretical and practical perspectives. However, verifying the theoretical analysis of HE-IES is challenging due to the limited availability of operational data for practical heating system (HS). This difficulty, in turn, poses challenges for system monitoring, state estimation, and optimized operation. To tackle these issues, in this article, we establish an HS platform based on a similarity model and conduct a series of HE-IES verification experiments. First, we derive the HS-scale model based on the similarity theory. With this model, the operating condition of practical HS can be reproduced in an experimental platform (EP). Then, we introduce two distinct sets of EP parameter ratio factors and propose an experimental verification framework for evaluating practical HS operation strategies and assessing the accuracy of simulations. With the proposed model and framework, we establish a nine-pipe, 12.5-m HS-EP and conduct two experiments. In the first experiment, we scrutinized the HS operation strategy generated by mainstream HE-IES optimization algorithms. The results unveiled that, during the experiment, the EP exceeded its security limits for 2.87 h—a deviation unanticipated by theoretical analysis. In the second experiment, we meticulously evaluated the accuracy of the HE-IES simulation algorithm. Our findings reveal minimal temperature errors, with an average of 0.1864 and a maximum of 0.622, validating the precision of the simulation algorithm.

The integrated energy system (IES) has bright prospects in engineering applications for its excellent performance in energy efficiency and renewable energy consumption. In the IES, the thermal comfort is affected by the heating power, buildings parameters, and outdoor temperatures simultaneously. Therefore, the uncertainty of the outdoor temperature will bring some adverse effects on thermal comfort, which need to be considered in the dispatch decision of the IES. In this article, we propose a day-ahead adaptive robust dispatch model (ARDM) for the IES to make a dispatch plan under the uncertainties of the net electrical-load and outdoor temperature, with the aim of guaranteeing the safe operation of IES and the thermal comfort of end-users. The thermal dynamic characteristics of the district heating network and buildings are utilized to provide operational flexibility and improve economic performance. To decrease the conservatism of dispatch results, the multi-interval uncertainty set is introduced to model the uncertainties. The ARDM model is a two-stage robust optimization with a linear recourse problem, and the column-and-constraint generation method is used to solve it. Two cases of different scale are studied to verify the effectiveness and advantages of the proposed method.