Kuijie Zhang

Designing effective graph neural networks (GNNs) for diverse tasks requires substantial manual effort, especially when dealing with the intricate interplay between topological structures and semantic information in graph data. Existing automated approaches often rely on off-the-shelf model combinations that remain superficial, resulting in generated model frameworks that are hardly interpretable and limited by the capabilities of the combined models. To address this gap, we propose an evolutionary-based framework that systematically searches for optimal GNN architectures while adaptively combining topological and semantic insights. This approach reduces human intervention, accommodates a wide range of graph tasks, and ensures robust performance in complex scenarios. Extensive experiments on real-world datasets demonstrate that our method outperforms both handcrafted GNNs and mainstream AutoML models in terms of accuracy, offering a scalable and adaptive solution for GNN design.

Accurate traffic flow forecasting is a fundamental yet challenging task in intelligent transportation systems, because of the highly nonlinear and complex nature of traffic dynamics. This paper presents a novel Spatio-Temporal Graph Neural Network with Integrated Semantics and Topology (STIGNN). Unlike existing approaches, STIGNN jointly exploits node-level semantic features and graph topological dependencies to enhance spatial representation learning. Specifically, spatial correlations are captured through a ChebNet–GAT hybrid mechanism, which combines multi-hop structural information with semantic attention. Temporal dependencies are modeled using a Gated Temporal Convolutional Network (Gated TCN), enabling efficient learning of long-range sequences. Furthermore, the dual-attention design over node semantics and network topology allows STIGNN to be directly applied to inductive prediction tasks, ensuring strong generalization across diverse network settings. Extensive experiments on two real-world benchmark datasets, METR-LA and PEMS-BAY, demonstrate that STIGNN consistently outperforms state-of-the-art baselines.

In recent years, graph neural networks have been widely used in multimedia information retrieval and other graph data processing tasks due to their powerful feature learning capabilities. However, existing graph neural network models typically handle only homogeneous graph data with simple structures and single semantics effectively. However, when faced with heterogeneous multimedia data characterized by complex interactions and rich semantics, the performance of traditional models degrades significantly. To address this challenge, this paper proposes a heterogeneous graph neural network algorithm based on meta-path random walk (MPRW-HGNN). First, we design a module at the meta-path instance level that generates meta-path instances and their structural representations via random walks. Then, a soft-attention mechanism is employed to fuse information from multiple meta-paths, better capturing the fine-grained semantic structures around nodes. Subsequently, we utilize a self-attention mechanism to explore semantic correlations and differences between multiple paths, enabling adaptive weighted fusion of multiple path information to generate robust node features for heterogeneous graph data. Through extensive experiments on information retrieval tasks using the IMDB movie dataset and DBLP academic paper dataset, we demonstrate the significant advantages of our proposed algorithm in handling multimodal data and improving retrieval accuracy.

Understanding user sentiment from multiple modalities is essential for applications such as personalized recommendations and affective computing. We propose TMJR, a Three-modal Joint Representation model for multimodal sentiment analysis, which introduces a structured three-round cross-modal attention mechanism to integrate textual, acoustic, and visual information progressively. Unlike prior one-pass or pairwise fusion methods, TMJR models multiple directional interaction paths to capture deeper cross-modal dependencies and improve semantic alignment. We evaluate TMJR on two benchmark datasets: CMU-MOSI and CMU-MOSEI. It achieves state-of-the-art results, with an F1 score of 86.4% and a Pearson correlation of 0.799 on MOSI, and an F1 score of 86.5% and a correlation of 0.775 on MOSEI. Further ablation, label-efficiency, and visualization analyses confirm the model’s robustness. TMJR provides a promising solution for sentiment-aware recommendation and multimodal user understanding.

Graph neural networks (GNNs), as a rising star in machine learning, are widely used in relational data models and have achieved outstanding performance in graph tasks. GNN continuously takes inspiration from mature models in other domains such as computer vision and natural language processing to motivate the development of graph algorithms. However, due to the various data structures from different domains, the cross-domain migration of models has to go through a long period of disassembly and reconstruction, which may not yield the desired results. To preserve the excellent properties of convolution and optimize the migration process from convolutional neural networks (CNNs) to GNNs, we propose a convolution bridge. The convolution bridge realizes the data alignment from CNN to GNN, so that the CNN-based model can be efficiently migrated to the graph structure model. To demonstrate the effectiveness of our migration strategy, we migrated the inception module and U-Net architecture from CNNs to GNNs, named GraInc and GraU-Net, for the node-level task and the graph-level task, respectively. Experimental results show that GraInc and GraU-Net are highly competitive compared to the current state-of-the-art models, particularly on dense graph datasets.