Mengxue Yang, Jinming Li, Chun Yang, Jiaqi Zhu, Jiafan Li, Guanhua Zhang, Ying Li. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

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.

Qihang Ai, Jiafan Li, Jincheng Dai, Jianwu Zhou, Lemao Liu, Haiyun Jiang, Shuming Shi. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Combining1 subjective evaluation with aesthetic criteria, this paper proposes an objective overall quality assessment method for graph layout algorithms. Firstly, we build the subjective rating database of graph layouts. The subjective experiment is designed to rate different graph layouts. Then, for each graph layout, we use the readability metrics of the layout as independent variables, the subjective score of users as the dependent variable, to establish the regression model. Through the regression model, we can get the overall quality score of a graph layout.

This paper investigates the optimal number of processors to execute a parallel job, whose speedup profile obeys Amdahl's law, on a large-scale platform subject to fail-stop and silent errors. We combine the traditional checkpointing and rollback recovery strategies with verification mechanisms to cope with both error sources. We provide an exact formula to express the execution overhead incurred by a periodic checkpointing pattern of length T and with P processors, and we give first-order approximations for the optimal values T* and P* as a function of the individual processor failure rate λind. A striking result is that P* is of the order λind-1/4if the checkpointing cost grows linearly with the number of processors, and of the order λind-1/3if the checkpointing cost stays bounded for any P. We conduct an extensive set of simulations to support the theoretical study. The results confirm the accuracy of first-order approximation under a wide range of parameter settings.