The rapid spread of fake news on social media has significantly increased the importance of computational detection methods. Graph-based approaches, particularly Graph Neural Networks (GNNs), have emerged as powerful tools for modeling news propagation patterns. Despite their potential, current GNN-based methods still face challenges in robustness and interpretability due to two key shortcomings: they inadequately filter out irrelevant user-induced noise within propagation graphs, and their shallow architectures fail to effectively capture the intricate long-range dependencies characteristic of news propagation. To overcome these limitations, we propose NEGT (Noise-filtering Enhanced Graph Transformer), a novel graph Transformer framework explicitly designed for fake news detection. NEGT introduces a noise-augmented information bottleneck strategy embedded within its self-attention mechanism, effectively identifying and removing task-irrelevant interactions. Additionally, we propose a novel relational propagation graph encoding a strategy that explicitly captures multi-scale user relationships and propagation depth, enabling NEGT to model long-sequence propagation dependencies accurately. Experiments on various benchmark datasets show that NEGT surpasses current methods in accuracy, noise robustness, and interpretability.

Facing climate change, the transformation to renewable energy poses stability challenges for power grids due to their reduced inertia and increased decentralization. Traditional dynamic stability assessments, crucial for safe grid operation with higher renewable shares, are computationally expensive and unsuitable for large-scale grids in the real world. Although multiple proofs in the network science have shown that network measures, which quantify the structural characteristics of networked dynamical systems, have the potential to facilitate basin stability prediction, no studies to date have demonstrated their ability to efficiently generalize to real-world grids. With recent breakthroughs in Graph Neural Networks (GNNs), we are surprised to find that there is still a lack of a common foundation about: Whether network measures can enhance GNNs' capability to predict dynamic stability and how they might help GNNs generalize to realistic grid topologies. In this paper, we conduct, for the first time, a comprehensive analysis of 48 network measures in GNN-based stability assessments, introducing two strategies for their integration into the GNN framework. We uncover that prioritizing measures with consistent distributions across different grids as the input or regarding measures as auxiliary supervised information improves the model's generalization ability to realistic grid topologies, even when models trained on only 20-node synthetic datasets are used. Our empirical results demonstrate a significant enhancement in model generalizability, increasing the$R^{2}$perforsmance from 66% to 83%. When evaluating the probabilistic stability indices on the realistic Texan grid model, GNNs reduce the time needed from 28,950 hours (Monte Carlo sampling) to just 0.06 seconds.

The rise of social media has intensified fake news risks, prompting a growing focus on leveraging graph learning methods such as graph neural networks (GNNs) to understand post-spread patterns of news. However, existing methods often produce less robust and interpretable results as they assume that all information within the propagation graph is relevant to the news item, without adequately eliminating noise from engaged users. Furthermore, they inadequately capture intricate patterns inherent in long-sequence dependencies of news propagation due to their use of shallow GNNs aimed at avoiding the over-smoothing issue, consequently diminishing their overall accuracy. In this paper, we address these issues by proposing the Propagation Structure-aware Graph Transformer (PSGT). Specifically, to filter out noise from users within propagation graphs, PSGT first designs a noise-reduction self-attention mechanism based on the information bottleneck principle, aiming to minimize or completely remove the noise attention links among task-irrelevant users. Moreover, to capture multi-scale propagation structures while considering long-sequence features, we present a novel relational propagation graph as a position encoding for the graph Transformer, enabling the model to capture both propagation depth and distance relationships of users. Extensive experiments demonstrate the effectiveness, interpretability, and robustness of our PSGT.

Network (or graph) sparsification accelerates many downstream analyses. For graph sparsification, sampling methods derived from local heuristic considerations are common in practice, due to their efficiency in generating sparse subgraphs using only local information. Filtering-based edge sampling is the most typical approach in this respect, yet it heavily depends on an appropriate definition of edge importance. Instead, we propose a generalized node-focused edge sampling framework by preserving scaled/expected local node characteristics. Apart from expected degrees, these local node characteristics include the expected number of triangles and the expected number of non-closed wedges associated with a node. From a technical point of view, we adapt a game-theoretic sampling method from uncertain graph generation to obtain sparse subgraphs that approximate the expected local properties. We include a tolerance threshold for much faster convergence. Within this framework, we provide appropriate algorithmic variants for sparsification. Moreover, we propose a network measure called tri-wedge assortativity for the selection of the most suitable variant when sparsifying a given network. Extensive experimental studies on functional climate, observed real-world, and synthetic networks show the effectiveness of our method in preserving overall structural network properties – on average consistently better than the state of the art.

Network (or graph) sparsification compresses a graph by removing inessential edges. By reducing the data volume, it accelerates or even facilitates many downstream analyses. Still, the accuracy of many sparsification methods, with filtering-based edge sampling being the most typical one, heavily relies on an appropriate definition of edge importance. Instead, we propose a different perspective with a generalized local-property-based sampling method, which preserves (scaled) local node characteristics. Apart from degrees, these local node characteristics we use are the expected (scaled) number of wedges and triangles a node belongs to. Through such a preservation, main complex structural properties are preserved implicitly. We adapt a game-theoretic framework from uncertain graph sampling by including a threshold for faster convergence (at least 4 times faster empirically) to approximate solutions. Extensive experimental studies on functional climate networks show the effectiveness of this method in preserving macroscopic to meso-scopic and microscopic network structural properties.

Many network analysis tasks like classification over nodes require careful efforts in engineering features used by learning algorithms. Most of recent studies have been made and succeeded in the field of static network representation learning. However, real-world networks are often dynamic and little work has been done on how to describe dynamic networks. In this work, we pose the problem of condensing dynamic networks and introduce SuRep, an encoding-decoding framework which utilizes matrix factorization technique to derive a succinct representation of a dynamic network in any stationary phase. We show that the succinct representation method can uncover the invariant structural properties in the network evolution and derive dense feature representations of the nodes as the byproduct. This method can be easily extended to dynamic attribute networks. For experiments on detecting change points in dynamic networks and network classification with real-world datasets we demonstrate SuRep's potential for capturing latent patterns among nodes.