Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While Transformer-based models have demonstrated strong performance by capturing long-range temporal dependencies, their reliance on self-attention results in quadratic complexity with respect to sequence length, limiting scalability on high-frequency or large-scale graphs. In this work, we revisit the necessity of self-attention in dynamic graph modeling. Inspired by recent findings that attribute the success of Transformers more to their architectural design than attention itself, we propose GLFormer, a novel attention-free Transformer-style framework for dynamic graphs. GLFormer introduces an adaptive token mixer that performs context-aware local aggregation based on interaction order and time intervals. To capture long-term dependencies, we further design a hierarchical aggregation module that expands the temporal receptive field by stacking local token mixers across layers. Experiments on six widely used dynamic graph benchmarks show that GLFormer achieves competitive or superior performance, which reveals that attention-free architectures can match or surpass Transformer baselines in dynamic graph settings with significantly improved efficiency.

Recent years have witnessed the rapid development of deep-learning-based, graph-neural-network-based forecasting methods for modern intelligent transportation systems. However, most existing work focuses exclusively on capturing spatio-temporal dependencies from historical traffic data, while overlooking the fact that suddenly occurring transportation incidents, such as traffic accidents and adverse weather, serve as external disturbances that can substantially alter temporal patterns. We argue that this issue has become a major obstacle to modeling the dynamics of traffic systems and improving prediction accuracy, but the unpredictability of incidents makes it difficult to observe patterns from historical sequences. To address these challenges, this paper proposes a novel framework named the Incident-Guided Spatiotemporal Graph Neural Network (IGSTGNN). IGSTGNN explicitly models the incident's impact through two core components: an Incident-Context Spatial Fusion (ICSF) module to capture the initial heterogeneous spatial influence, and a Temporal Incident Impact Decay (TIID) module to model the subsequent dynamic dissipation. To facilitate research on the spatio-temporal impact of incidents on traffic flow, a large-scale dataset is constructed and released, featuring incident records that are time-aligned with traffic time series. On this new benchmark, the proposed IGSTGNN framework is demonstrated to achieve state-of-the-art performance. Furthermore, the generalizability of the ICSF and TIID modules is validated by integrating them into various existing models.

With the development and widespread application of large language models (LLMs), the new paradigm of "Model as Product" is rapidly evolving, and demands higher capabilities to address complex user needs, often requiring precise workflow execution which involves the accurate understanding of multiple tasks.However, existing benchmarks focusing on single-task environments with limited constraints lack the complexity required to fully reflect real-world scenarios.To bridge this gap, we present the Extremely Complex Instruction Following Benchmark (EIFBENCH), meticulously crafted to facilitate a more realistic and robust evaluation of LLMs.EIFBENCH not only includes multi-task scenarios that enable comprehensive assessment across diverse task types concurrently, but also integrates a variety of constraints, replicating complex operational environments.Furthermore, we propose the Segment Policy Optimization (SegPO) algorithm to enhance the LLM's ability to accurately fulfill multi-task workflow.Evaluations on EIFBENCH have unveiled considerable performance discrepancies in existing LLMs when challenged with these extremely complex instructions.This finding underscores the necessity for ongoing optimization to navigate the intricate challenges posed by LLM applications.

Dynamic graph learning equips the edges with time attributes and allows multiple links between two nodes, which is a crucial technology for understanding evolving data scenarios like traffic prediction and recommendation systems. Existing works obtain the evolving patterns mainly depending on the most recent neighbor sequences. However, we argue that whether two nodes will have interaction with each other in the future is highly correlated with the same interaction that happened in the past. Only considering the recent neighbors overlooks the phenomenon of repeat behavior and fails to accurately capture the temporal evolution of interactions. To fill this gap, this paper presents RepeatMixer, which considers evolving patterns of first and high-order repeat behavior in the neighbor sampling strategy and temporal information learning. Firstly, we define the first-order repeat-aware nodes of the source node as the destination nodes that have interacted historically and extend this concept to high orders as nodes in the destination node's high-order neighbors. Then, we extract neighbors of the source node that interacted before the appearance of repeat-aware nodes with a slide window strategy as its neighbor sequence. Next, we leverage both the first and high-order neighbor sequences of source and destination nodes to learn temporal patterns of interactions via an MLP-based encoder. Furthermore, considering the varying temporal patterns on different orders, we introduce a time-aware aggregation mechanism that adaptively aggregates the temporal representations from different orders based on the significance of their interaction time sequences. Experimental results demonstrate the superiority of RepeatMixer over state-of-the-art models in link prediction tasks, underscoring the effectiveness of the proposed repeat-aware neighbor sampling strategy.

Accurate prediction of what types of patents that companies will apply for in the next period of time can figure out their development strategies and help them discover potential partners or competitors in advance. Although important, this problem has been rarely studied in previous research due to the challenges in modeling companies-continuously evolving preferences and capturing the semantic correlations of classification codes. To fill this gap, we propose an event-based dynamic graph learning framework for patent application trend prediction. In particular, our method is founded on the memorable representations of both companies and patent classification codes. When a new patent is observed, the representations of the related companies and classification codes are updated according to the historical memories and the currently encoded messages. Moreover, a hierarchical message passing mechanism is provided to capture the semantic proximities of patent classification codes by updating their representations along the hierarchical taxonomy. Finally, the patent application trend is predicted by aggregating the representations of the target company and classification codes from static, dynamic and hierarchical perspectives. Experiments on real-world data demonstrate the effectiveness of our approach under various experimental conditions, and also reveal the abilities of our method in learning semantics of classification codes and tracking technology developing trajectories of companies.

Patent classification aims to assign multiple International Patent Classification (IPC) codes to a given patent. Existing methods for automated patent classification primarily focus on analyzing the text descriptions of patents. However, apart from the textual information, each patent is also associated with some assignees, and the knowledge of their previously applied patents can often be valuable for accurate classification. Furthermore, the hierarchical taxonomy defined by the IPC system provides crucial contextual information and enables models to leverage the correlations between IPC codes for improved classification accuracy. However, existing methods fail to incorporate the above aspects and lead to reduced performance. To address these limitations, we propose an integrated framework that comprehensively considers patent-related information for patent classification. To be specific, we first present an IPC codes correlations learning module to capture both horizontal and vertical information within the IPC codes. This module effectively captures the correlations by adaptively exchanging and aggregating messages among IPC codes at the same level (horizontal information) and from both parent and children codes (vertical information), which allows for a comprehensive integration of knowledge and relationships within the IPC hierarchical taxonomy. Additionally, we design a historical application patterns learning component to incorporate previous patents of the corresponding assignee by aggregating high-order temporal information via a dual-channel graph neural network. Finally, our approach combines the contextual information from patent texts, which encompasses the semantics of IPC codes, with assignees’ sequential preferences to make predictions. Experimental evaluations on real-world datasets demonstrate the superiority of our proposed approach over existing methods. Moreover, we present the model’s ability to capture the temporal patterns of assignees and the semantic dependencies among IPC codes.

Due to the increasing diversification of urban transportation modes, many urban areas have the problem of unbalanced traffic demand, which makes accurate prediction of traffic demand very important. However, most of the existing studies focus on improving the prediction accuracy of traffic demand on the single spatial relationship of a single traffic mode, ignoring the diversity of spatial relationships and the heterogeneity of transportation stations in the traffic network. In this paper, we propose a Co-Modal Graph Attention neTwork(CMGAT) framework to uncover the impact of different spatial relationships and traffic mode interactions on traffic demand. Specifically, we first utilize a feature embedding block to capture the semantic information from several features. Then, a multiple traffic graphs-based spatial attention mechanism and a multiple time periods-based temporal attention mechanism are proposed to capture spatial and temporal dependencies in multi-mode traffic demands. Moreover, an output layer is provided to incorporate the hidden states and raw time sequences to predict future traffic demand. Finally, we conduct experiments on two real-world datasets, NYC Bike and NYC Taxi, and the results not only demonstrate the superiority of our model, but also indicate the necessity of considering multiple spatial relationships and traffic modes.