Author name cluster

Song Yang

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.

5 papers

1 author row

TAAS Journal 2025 Journal Article

Combining Personalized Federated Hypernetworks and Shared Residual Learning for Distributed QoS Prediction

Guobing Zou
Shiyi Lin
Shaogang Wu
Shengxiang Hu
Song Yang
Yanglan Gan
Bofeng Zhang
Yixin Chen

Connected vehicles due to the high mobility and dynamic network topologies of connected vehicles require accurate QoS that includes high throughput and low latency to assess satisfactory QoE. Existing methods mainly focus on centralized QoS prediction while paying little attention to distributed mobile QoS prediction, making it challenging to protect user privacy information when invoking Web services. Moreover, even though some advanced centralized methods can be transformed into federated architectures, they often face difficulty in capturing latent feature representations of users and services and learning personalized prediction layers between them due to the heterogeneity of the QoS dataset. To address the above issues, we propose a novel framework for distributed QoS prediction, called Combining Personalized Federated Hypernetworks and Shared Residual Learning for Distributed QoS Prediction (FHR-DQP). FHR-DQP adopts the federated averaging (FedAvg) to aggregate location-aware residual shared feature information across all clients. Additionally, a hypernetwork is leveraged to generate personalized networks for user-service QoS prediction in each client. These components are integrated as a hybrid framework that performs training using a federated approach and makes personalized QoS predictions within each client. Extensive experiments are conducted on a real-world benchmark QoS dataset called WS-DREAM, containing nearly 2,000,000 historical QoS invocation records. Compared with both centralized and federated competing baselines, the results demonstrate that FHR-DQP achieves the highest performance for distributed QoS prediction, when it provides privacy-preserving of users’ QoS invocations.

Details DOI

AAMAS Conference 2025 Conference Paper

Data Pricing for Graph Neural Networks without Pre-purchased Inspection

Yiping Liu
Mengxiao Zhang
Jiamou Liu
Song Yang

Machine learning (ML) models have become essential tools in various scenarios. Their effectiveness, however, hinges on a substantial volume of data for satisfactory performance. Model marketplaces have thus emerged as crucial platforms bridging model consumers seeking ML solutions and data owners possessing valuable data. These marketplaces leverage model trading mechanisms to properly incentive data owners to contribute their data, and return a well performing ML model to the model consumers. However, existing model trading mechanisms often assume the data owners are willing to share their data before being paid, which is not reasonable in real world. Given that, we propose a novel mechanism, named Structural Importance based Model Trading (SIMT) mechanism, that assesses the data importance and compensates data owners accordingly without disclosing the data. Specifically, SIMT procures feature and label data from data owners according to their structural importance, and then trains a graph neural network for model consumers. Theoretically, SIMT ensures incentive compatible, individual rational and budget feasible. The experiments on five popular datasets validate that SIMT consistently outperforms vanilla baselines by up to 40% in both MacroF1 and MicroF1.

PDF

AAAI Conference 2025 Conference Paper

Large Language Model Meets Graph Neural Network in Knowledge Distillation

Shengxiang Hu
Guobing Zou
Song Yang
Shiyi Lin
Yanglan Gan
Bofeng Zhang
Yixin Chen

While Large Language Models (LLMs) show promise for Text-Attributed Graphs (TAGs) learning, their deployment is hindered by computational demands. Graph Neural Networks (GNNs) are efficient but struggle with TAGs' complex semantics. We propose LinguGKD, a novel LLM-to-GNN knowledge distillation framework that enables transferring both local semantic details and global structural information from LLMs to GNNs. First, it introduces TAG-oriented instruction tuning, enhancing LLMs with graph-specific knowledge through carefully designed prompts. Next, it develops a layer-adaptive multi-scale contrastive distillation strategy aligning LLM and GNN features at multiple granularities, from node-level to graph-level. Finally, the distilled GNNs combine the semantic richness of LLMs with the computational efficiency of traditional GNNs. Experiments demonstrate that LinguGKD outperforms existing graph distillation frameworks, the distilled simple GNNs achieve comparable or superior performance to more complex GNNs and teacher LLMs, while maintaining computational efficiency. This work bridges the gap between LLMs and GNNs, facilitating advanced graph learning in resource-constrained environments and providing a framework to leverage ongoing LLM advancements for GNN improvement.

PDF Details DOI

AAAI Conference 2023 Conference Paper

USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network

Yifei Wang
Yupan Wang
Zeyu Zhang
Song Yang
Kaiqi Zhao
Jiamou Liu

Unsupervised/self-supervised graph neural networks (GNN) are susceptible to the inherent randomness in the input graph data, which adversely affects the model's performance in downstream tasks. In this paper, we propose USER, an unsupervised and robust version of GNN based on structural entropy, to alleviate the interference of graph perturbations and learn appropriate representations of nodes without label information. To mitigate the effects of undesirable perturbations, we analyze the property of intrinsic connectivity and define the intrinsic connectivity graph. We also identify the rank of the adjacency matrix as a crucial factor in revealing a graph that provides the same embeddings as the intrinsic connectivity graph. To capture such a graph, we introduce structural entropy in the objective function. Extensive experiments conducted on clustering and link prediction tasks under random-perturbation and meta-attack over three datasets show that USER outperforms benchmarks and is robust to heavier perturbations.

PDF Details DOI

YNICL Journal 2019 Journal Article

A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas

Chong Qi
Yiming Li
Xing Fan
Yin Jiang
Rui Wang
Song Yang
Lanxi Meng
Tao Jiang

OBJECTIVES: H-MRS) metabolic features and the grade of gliomas, and to establish a machine-learning model to predict the glioma grade. METHODS: H-MRS image. The Student's t-test was conducted to screen for differentially expressed features between low- and high-grade gliomas (WHO grades II and III/IV, respectively). Next, the minimum Redundancy Maximum Relevance (mRMR) algorithm was performed to further select features for a support vector machine (SVM) classifier building. Performance of the predictive model was evaluated both in the training and validation sets using ROC curve analysis. RESULTS: H-MRS metabolic features, thirteen features were differentially expressed. Four features were further selected as grade-predictive imaging signatures using the mRMR algorithm. The predictive performance of the machine-learning model measured by the AUC was 0.825 and 0.820 in the training and validation sets, respectively. This was better than the predictive performances of individual metabolic features, the best of which was 0.812. CONCLUSIONS: H-MRS metabolic features could help in predicting the grade of gliomas. The machine-learning model achieved a better prediction performance in grading gliomas than individual features, indicating that it could complement the traditionally used metabolic features.

Details DOI