Author name cluster

Jiaxing He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICML Conference 2025 Conference Paper

Graph Generative Pre-trained Transformer

Xiaohui Chen
Yinkai Wang
Jiaxing He
Yuanqi Du
Soha Hassoun
Xiaolin Xu
Liping Liu 0001

Graph generation is a critical task in numerous domains, including molecular design and social network analysis, due to its ability to model complex relationships and structured data. While most modern graph generative models utilize adjacency matrix representations, this work revisits an alternative approach that represents graphs as sequences of node set and edge set. We advocate for this approach due to its efficient encoding of graphs and propose a novel representation. Based on this representation, we introduce the Graph Generative Pre-trained Transformer (G2PT), an auto-regressive model that learns graph structures via next-token prediction. To further exploit G2PT’s capabilities as a general-purpose foundation model, we explore fine-tuning strategies for two downstream applications: goal-oriented generation and graph property prediction. We conduct extensive experiments across multiple datasets. Results indicate that G2PT achieves superior generative performance on both generic graph and molecule datasets. Furthermore, G2PT exhibits strong adaptability and versatility in downstream tasks from molecular design to property prediction.

Details

EAAI Journal 2025 Journal Article

Study on the deformation mode domain of shrink energy-absorbing structures based on curve feature classification method

Jiaxing He
Ping Xu
Jie Xing
Shuguang Yao
Bo Wang
Xin Zheng

Shrink energy-absorbing structures play a key role in engineering applications by absorbing impact energy and ensuring passenger safety. However, inappropriate structural parameters and contact conditions can lead to buckling instability or folding collapse, which reduces the energy absorption efficiency. For this purpose, a deformation mode classification method based on the curve feature was proposed. A Long Short Term Memory (LSTM) network was used to predict the crushing force curve, followed by feature extraction and mode classification to establish the mapping relationships from design parameters to deformation modes. The deformation mode domain was then constructed using the classification model for data expansion, and its boundaries were precisely defined using surface fitting techniques. The critical cone angles of the shrink deformation mode at different friction coefficients were obtained by two-dimensional analysis. In addition, a structural design strategy was also proposed to maximize the specific energy absorption (SEA) of the structure under the shrink deformation mode. The results show that the classification method can effectively predict the deformation modes with 97 % accuracy. Further analysis of the deformation mode domain reveals that the critical cone angle of the shrink deformation mode decreases with the increase of the friction coefficient. Overall, this study predicts the deformation modes of shrink energy-absorbing structures and analyzes the variation of the critical cone angle, providing important guidance for structural optimization and improving energy absorption efficiency.

Details DOI

NeurIPS Conference 2024 Conference Paper

GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction

Shijin Duan
Ruyi Ding
Jiaxing He
Aidong A. Ding
Yunsi Fei
Xiaolin Xu

Graph-structured data is integral to many applications, prompting the development of various graph representation methods. Graph autoencoders (GAEs), in particular, reconstruct graph structures from node embeddings. Current GAE models primarily utilize self-correlation to represent graph structures and focus on node-level tasks, often overlooking multi-graph scenarios. Our theoretical analysis indicates that self-correlation generally falls short in accurately representing specific graph features such as islands, symmetrical structures, and directional edges, particularly in smaller or multiple graph contexts. To address these limitations, we introduce a cross-correlation mechanism that significantly enhances the GAE representational capabilities. Additionally, we propose the GraphCroc, a new GAE that supports flexible encoder architectures tailored for various downstream tasks and ensures robust structural reconstruction, through a mirrored encoding-decoding process. This model also tackles the challenge of representation bias during optimization by implementing a loss-balancing strategy. Both theoretical analysis and numerical evaluations demonstrate that our methodology significantly outperforms existing self-correlation-based GAEs in graph structure reconstruction.

PDF Details DOI

ICML Conference 2023 Conference Paper

Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling

Xiaohui Chen
Jiaxing He
Xu Han 0012
Liping Liu 0001

Diffusion-based generative graph models have been proven effective in generating high-quality small graphs. However, they need to be more scalable for generating large graphs containing thousands of nodes desiring graph statistics. In this work, we propose EDGE, a new diffusion-based generative graph model that addresses generative tasks with large graphs. To improve computation efficiency, we encourage graph sparsity by using a discrete diffusion process that randomly removes edges at each time step and finally obtains an empty graph. EDGE only focuses on a portion of nodes in the graph at each denoising step. It makes much fewer edge predictions than previous diffusion-based models. Moreover, EDGE admits explicitly modeling the node degrees of the graphs, further improving the model performance. The empirical study shows that EDGE is much more efficient than competing methods and can generate large graphs with thousands of nodes. It also outperforms baseline models in generation quality: graphs generated by our approach have more similar graph statistics to those of the training graphs.

Details