Nowadays, numerous online platforms can be described as multi-modal heterogeneous networks (MMHNs), such as Douban's movie networks and Amazon's product review networks. Accurately categorizing nodes within these networks is crucial for analyzing the corresponding entities, which requires effective representation learning on nodes. However, existing multi-modal fusion methods often adopt either early fusion strategies which may lose the unique characteristics of individual modalities, or late fusion approaches overlooking the cross-modal guidance in GNN-based information propagation. In this paper, we propose a novel model for node classification in MMHNs, named Heterogeneous Graph Neural Network with Inter-Modal Attention (HGNN-IMA). It learns node representations by capturing the mutual influence of multiple modalities during the information propagation process, within the framework of heterogeneous graph transformer. Specifically, a nested inter-modal attention mechanism is integrated into the inter-node attention to achieve adaptive multi-modal fusion, and modality alignment is also taken into account to encourage the propagation among nodes with consistent similarities across all modalities. Moreover, an attention loss is augmented to mitigate the impact of missing modalities. Extensive experiments validate the superiority of the model in the node classification task, providing an innovative view to handle multi-modal data, especially when accompanied with network structures. The full version including Appendix is available at http://arxiv.org/abs/2505.07895.

Recently, rule-based time series classification models are widely used in safety-critical scenarios demanding strong interpretability, through providing explicit and rigorous rationales. However, due to the discrepancy between discrete rules and continuous neural networks, the generated rules are not completely consistent with the actual decision-making process, rendering users hesitant to trust the model. Additionally, existing methods learn the role (weight) of each time point independently, which is not in line with human understanding and the consecutive nature of temporal properties. In this paper, we propose a novel neuro-symbolic model named TemporalRule, aiming to automatically learn Signal Temporal Logic (STL) rules for interpretable time series classification. Our model directly optimizes the neural networks representing discrete rules via gradient grafting, producing reliable rules that can exactly determine the classification results. Notably, a temporal logical layer is designed to simulate expressive temporal operators, including one 2-predicate operator (Until) and two 2-level composite operators (EA and AE), through adaptively learning the time bounds of involved intervals. That creates consistent weights for consecutive time points, enhancing the intuitiveness of derived rules. Extensive experiments on diverse real-world datasets in safety-critical domains show that TemporalRule achieves superior and stable classification accuracy compared to state-of-the-art rule-based approaches, and the learned rules can precisely and concisely explicate the classification results, leading to a trustable model.

Accurately forecasting traffic flow using time-series data from multimedia sensors remains a significant challenge, despite its importance for advancing intelligent transportation systems. Recent advancements in attention-based models have shown promise in capturing spatial-temporal dependencies in traffic flow data. Yet, these models exhibit three principal limitations: (1) they employ either factorized or coupled spatial-temporal attention mechanisms, potentially failing to fully harness the potential of these distinct approaches; (2) the attention allocation for spatial nodes is predominantly data-centric, which may overlook existing knowledge about the nodes' importance within the transportation network; (3) while traditional attention-based methods effectively capture long-term dependencies, they often struggle with adapting to the disparate lengths of temporal contexts. To overcome these limitations, we introduce a multi-way framework dubbed FEST that innovatively integrates both factorized and coupled spatial-temporal attention mechanisms. We then enhance FEST by incorporating PageRank-derived node importance scores to guide focus on nodes. Moreover, a novel multi-scale temporal learning approach is proposed to improve model capability with both long- and short-term temporal dynamics. Extensive experiments on real-world datasets under long- and short-term prediction scenarios confirm the effectiveness of our method.

Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment, since it requires only a limited set of seed words (label names) for each category instead of labeled data. With the help of recently popular prompting Pre-trained Language Models (PLMs), many studies leveraged manually crafted and/or automatically identified verbalizers to estimate the likelihood of categories, but they failed to differentiate the effects of these category-indicative words, let alone capture their correlations and realize adaptive adjustments according to the unlabeled corpus. In this paper, in order to let the PLM effectively understand each category, we at first propose a novel form of rule-based knowledge using logical expressions to characterize the meanings of categories. Then, we develop a prompting PLM-based approach named RulePrompt for the WSTC task, consisting of a rule mining module and a rule-enhanced pseudo label generation module, plus a self-supervised fine-tuning module to make the PLM align with this task. Within this framework, the inaccurate pseudo labels assigned to texts and the imprecise logical rules associated with categories mutually enhance each other in an alternative manner. That establishes a self-iterative closed loop of knowledge (rule) acquisition and utilization, with seed words serving as the starting point. Extensive experiments validate the effectiveness and robustness of our approach, which markedly outperforms state-of-the-art weakly supervised methods. What is more, our approach yields interpretable category rules, proving its advantage in disambiguating easily-confused categories.

Anomaly detection, particularly the detection of anomalous behaviors in dynamic and heterogeneous social networks, is becoming more and more crucial in real life. Traditional rule-based and feature-based methods cannot well capture the structural and temporal patterns of ever-changing user behaviors. Moreover, most of the existing works based on network embedding either rely on discretized snapshots, which have ignored accurate temporal relations among user behaviors and weakened the impact of new edges, or fail to utilize dynamic and heterogeneous information simultaneously to distinguish varying effects of new edges on existing nodes. In this paper, we propose an end-to-end continuous-time model, named Temporal Heterogeneous Graph Neural Network (THGNN), to detect anomalous behaviors (edges) in dynamic heterogeneous social networks. Specifically, the model constantly updates node embeddings by propagating the information of a new edge to its source and target nodes as well as their neighbors. In this process, heterogeneous encoders are employed to handle different types of nodes and edges. What is more, a novel dual-level distributive attention mechanism is designed to allocate the influence degree of a currently interacting node to its multiple neighbors, considering the combined effect of edge type and time interval information. That can be regarded as an extension of the classical aggregative attention mechanism in the opposite direction. Extensive experiments on four real-world datasets demonstrate that THGNN outperforms all the baselines on the task of anomalous edge detection, achieving an average AUC gain of 6% across all datasets.