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.

Diffusion probabilistic models (DPMs) have recently demonstrated impressive generative capabilities. There is emerging evidence that their sample reconstruction ability can yield meaningful representations for recognition tasks. In this paper, we demonstrate that the objectives underlying generation and representation learning are not perfectly aligned. Through a spectral analysis, we find that minimizing the mean squared error (MSE) between the original graph and its reconstructed counterpart does not necessarily optimize representations for downstream tasks. Instead, focusing on reconstructing a small subset of features, specifically those capturing global information, proves to be more effective for learning powerful representations. Motivated by these insights, we propose a novel framework, the Smooth Diffusion Model for Graphs (SDMG), which introduces a multi-scale smoothing loss and low-frequency information encoders to promote the recovery of global, low-frequency details, while suppressing irrelevant high-frequency noise. Extensive experiments validate the effectiveness of our method, suggesting a promising direction for advancing diffusion models in graph representation learning.

In recent years, Embodied Artificial Intelligence (Embodied AI) has advanced rapidly, yet the increasing size of models conflicts with the limited computational capabilities of Embodied AI platforms. To address this challenge, we aim to achieve both high model performance and practical deployability. Specifically, we focus on Vision-and-Language Navigation (VLN), a core task in Embodied AI. This paper introduces a two-stage knowledge distillation framework, producing a student model, MiniVLN, and showcasing the significant potential of distillation techniques in developing lightweight models. The proposed method aims to capture fine-grained knowledge during the pretraining phase and navigation-specific knowledge during the fine-tuning phase. Our findings indicate that the two-stage distillation approach is more effective in narrowing the performance gap between the teacher model and the student model compared to single-stage distillation. On the public R2R and REVERIE benchmarks, MiniVLN achieves performance on par with the teacher model while having only about 12 % of the teacher model's parameter count.

Goal-Oriented Vision-and-Language Navigation (VLN) aims to enable agents to navigate to specified locations and identify designated target objects following natural language instruction. This approach has gained popularity due to its close alignment with real-world scenarios. However, existing studies have predominantly focused on enhancing navigation performance, neglecting the ability to locate objects at the navigation endpoint. This oversight has resulted in a significant discrepancy between the success rates of navigation and object grounding. The challenge is compounded by the complex reasoning required by the instructions and the necessity to synthesize multiperspective images of objects, which overwhelms traditional object grounding methods. We leverage the Multi-Modal Large Language Model (MLLM) to bridge this gap, allowing agents to seek assistance from these models when struggling to locate the target object. The agent conducts a multi-stage evaluation to discern the cause of its confusion and promptly extracts and updates the most relevant information for MLLM to assess. Our method is plug-and-play and model-agnostic, facilitating integration with numerous existing VLN strategies without the need for retraining. Implementing our approach across four distinct methods has improved performance on the REVERIE and SOON datasets, demonstrating the effectiveness and generalizability of our technique.

Applying deep learning to predict patient prognostic survival outcomes using histological whole-slide images (WSIs) and genomic data is challenging due to the morphological and transcriptomic heterogeneity present in the tumor microenvironment. Existing deep learning-enabled methods often exhibit learning biases, primarily because the genomic knowledge used to guide directional feature extraction from WSIs may be irrelevant or incomplete. This results in a suboptimal and sometimes myopic understanding of the overall pathological landscape, potentially overlooking crucial histological insights. To tackle these challenges, we propose the CounterFactual Bidirectional Co-Attention Transformer framework. By integrating a bidirectional co-attention layer, our framework fosters effective feature interactions between the genomic and histology modalities and ensures consistent identification of prognostic features from WSIs. Using counterfactual reasoning, our model utilizes causality to model unimodal and multimodal knowledge for cancer risk stratification. This approach directly addresses and reduces bias, enables the exploration of 'what-if' scenarios, and offers a deeper understanding of how different features influence survival outcomes. Our framework, validated across eight diverse cancer benchmark datasets from The Cancer Genome Atlas (TCGA), represents a major improvement over current histology-genomic model learning methods. It shows an average 2.5% improvement in c-index performance over 18 state-of-the-art models in predicting patient prognoses across eight cancer types.

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.

Cervical cancer is the fourth most common cancer in women and its subtyping requires examining histopathological slides or digital images, such as whole slide images (WSIs). However, manually inspecting WSIs with gigapixel sizes can be laborious and prone to errors for pathologists. To address this issue, computer-aided approaches based on weakly-supervised learning techniques have been proposed. These methods can predict disease types directly from WSIs and highlight diagnosis-relevant regions, which can help pathologists achieve faster and more accurate diagnoses. WSIs are divided into overlapping patches using a sliding window approach, and these patches are subsequently screened in a sequential zig-zag pattern to identify spatiotemporal dependencies. These dependencies are further analyzed to generate predictions at the WSI level. Therefore, effective patch feature learning and spatiotemporal aggregation are two key issues in the weakly-supervised WSI classification (WSWC) task. In this paper, we present a label-efficient WSWC method called spatiotemporal aggregation for cervical WSIs (SAC-Net), which jointly performs online feature extraction and feature aggregation to infer the WSI-level prediction in an end-to-end manner. The online feature extractor helps to learn cervical-cancer-specific features and obtain more accurate patch representations. The feature aggregator uses an online instance clustering method to learn proper weight parameters for each cluster, which generates the WSI embedding with enhanced spatiotemporal aggregation. SAC-Net is developed and evaluated on a public cervical WSI dataset (TissueNet) containing 1015 WSIs, which are also externally tested on three independent cervical WSI datasets. Our results demonstrate that SAC-Net achieves state-of-the-art classification performance and is robust. SAC-Net has the potential to be a useful tool for clinical cervical cancer detection.

Cervical cytology is a critical screening strategy for early detection of pre-cancerous and cancerous cervical lesions. The challenge lies in accurately classifying various cervical cytology cell types. Existing automated cervical cytology methods are primarily trained on databases covering a narrow range of coarse-grained cell types, which fail to provide a comprehensive and detailed performance analysis that accurately represents real-world cytopathology conditions. To overcome these limitations, we introduce HiCervix, the most extensive, multi-center cervical cytology dataset currently available to the public. HiCervix includes 40,229 cervical cells from 4,496 whole slide images, categorized into 29 annotated classes. These classes are organized within a three-level hierarchical tree to capture fine-grained subtype information. To exploit the semantic correlation inherent in this hierarchical tree, we propose HierSwin, a hierarchical vision transformer-based classification network. HierSwin serves as a benchmark for detailed feature learning in both coarse-level and fine-level cervical cancer classification tasks. In our comprehensive experiments, HierSwin demonstrated remarkable performance, achieving 92.08% accuracy for coarse-level classification and 82.93% accuracy averaged across all three levels. When compared to board-certified cytopathologists, HierSwin achieved high classification performance (0.8293 versus 0.7359 averaged accuracy), highlighting its potential for clinical applications. This newly released HiCervix dataset, along with our benchmark HierSwin method, is poised to make a substantial impact on the advancement of deep learning algorithms for rapid cervical cancer screening and greatly improve cancer prevention and patient outcomes in real-world clinical settings.

Graph representation learning has re-emerged as a fascinating research topic due to the successful application of graph convolutional networks (GCNs) for graphs and inspires various downstream tasks, such as node classification and link prediction. Nevertheless, existing GCN-based methods for graph representation learning mainly focus on static graphs. Although some methods consider the dynamic characteristics of networks, the global structure information, which helps a node to gain worthy features from distant but valuable nodes, has not received enough attention. Moreover, these methods generally update the features of the nodes by averaging the features of neighboring nodes, which may not effectively consider the importance of different neighboring nodes during the aggregation. In this article, we propose a novel representation learning for dynamic graphs based on the GCNs, called DGCN. More specifically, the long short-term memory (LSTM) is utilized to update the weight parameters of GCN for capturing the global structure information across all time steps of dynamic graphs. Besides, a new Dice similarity is proposed to overcome the problem that the influence of directed neighbors is unnoticeable, which is further used to guide the aggregation. We evaluate the performance of the proposed method in the field of node clustering and link prediction, and the experimental results show a generally better performance of our proposed DGCN than baseline methods.

Community structure division is a crucial problem in the field of network data analysis. Algorithms based on Markov chains are easy to use and provide promising solutions for community detection. In a Markov chain-based algorithm (i.e., MCL), a flow distribution matrix and a transition matrix are used to describe stochastic flows and transition probabilities, respectively, on a network. The dynamic interaction process between stochastic flows and transition probabilities in MCLs is manifested through an iterative process of updating the abovementioned two matrices. As one of the key mechanisms of MCLs, such a dynamic process for increasing the inhomogeneity directly affects the accuracy and computational cost of MCL-based methods. Inspired by a kind of positive feedback interaction of a dendritic network of tube-like amoeba cell pseudopodia (named thePhysarumforaging network), aPhysarum-inspired relationship among vertices is proposed to enhance the transition probability in the dynamic process of MCL-based community detection algorithms. Specifically, the proposed hybrid community detection algorithm can adaptively search for a better combination of parameters based on a genetic algorithm. Some experiments are carried out on both static and dynamic networks. The results show that the uniquePhysaruminspired algorithm achieved better computational efficiency and detection performance than other algorithms.

Network embedding has become a fascinating research subject in recent years owing to its ability to represent networks with rich relationships in the low-dimensional vector space, which inspires various downstream tasks, such as link prediction and node classification. Nevertheless, most existing network embedding methods focus on static networks where nodes and edges do not evolve with time. Although some methods consider the dynamics of networks, they pay little attention to the global information of networks, or have recourse to node labels for training. In this paper, we propose an unsupervised dynamic network embedding using the global information, called UDNGI. More specifically, we first maximize the mutual information between the local node embedding and the global network embedding based on a well-designed graph convolutional network for capturing the global information at a time-step specific snapshot network. Then, a temporal smoothness constraint is proposed to minimize the embedding deviation between two successive snapshots, and a modified long short-term memory is designed to update the weight parameters of the graph convolutional network, which enables the model to capture the global information across all time steps. Extensive experiments on node classification and link prediction demonstrate that UDNGI achieves a generally better performance than state-of-the-art methods.