Mengyu Li

Mengyu Li

Auto-generated profile, based on publicly available information

Mengyu Li

College of Computer Science and Technology, Jilin University, Changchun, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 July 2022
Verified
Conference Paper
Open access
YLYonghao Liu
Yonghao Liu
MLMengyu Li
Mengyu Li
Ximing LiXiming Li
Ximing Li
FGFausto Giunchiglia
Fausto Giunchiglia
XFXiaoyue Feng
Xiaoyue Feng
RGRenchu Guan
Renchu Guan
Attributed networks, as a manifestation of data in non-Euclidean domains, have a wide range of applications in the real world, such as molecular property prediction, social network analysis and anomaly detection. Node classification, as a fundamental research problem in attributed networks, has attracted increasing attention among research communities. However, most existing models cannot be directly applied to the data with limited labeled instances (\textiti.e., the few-shot scenario). Few-shot node classification on attributed networks is gradually becoming a research hotspot. Although several methods aim to integrate meta-learning with graph neural networks to address this problem, some limitations remain. First, they all assume node representation learning using graph neural networks in homophilic graphs. %Hence, suboptimal performance is obtained when these models are applied to heterophilic graphs. Second, existing models based on meta-learning entirely depend on instance-based statistics. %which in few-shot settings are unavoidably degraded by data noise or outliers. Third, most previous models treat all sampled tasks equally and fail to adapt their uniqueness. %which has a significant impact on the overall performance of the model. To solve the above three limitations, we propose a novel graph Meta -learning framework called G raph learning based on P rototype and S caling & shifting transformation (Meta-GPS ). More specifically, we introduce an efficient method for learning expressive node representations even on heterophilic graphs and propose utilizing a prototype-based approach to initialize parameters in meta-learning. Moreover, we also leverage S$^2$ (scaling & shifting) transformation to learn effective transferable knowledge from diverse tasks. Extensive experimental results on six real-world datasets demonstrate the superiority of our proposed framework, which outperforms other state-of-the-art baselines by up to 13% absolute improvement in terms of related metrics.

24 October 2024 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
YLYonghao Liu
Yonghao Liu
MLMengyu Li
Mengyu Li
Ximing LiXiming Li
Ximing Li
LHLan Huang
Lan Huang
FGFausto Giunchiglia
Fausto Giunchiglia
RGRenchu Guan
Renchu Guan
Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning with graph neural networks to solve few-shot node classification on graphs. Despite their promising performance, some limitations remain. First, they employ the node encoding mechanism of homophilic graphs to learn node embeddings, even in heterophilic graphs. Second, existing models based on meta-learning ignore the interference of randomness in the learning process. Third, they are trained using only limited labeled nodes within the specific task, without explicitly utilizing numerous unlabeled nodes. Finally, they treat almost all sampled tasks equally without customizing them for their uniqueness. To address these issues, we propose a novel framework for few-shot node classification called Meta-GPS \(++\) . Specifically, we first adopt an efficient method to learn discriminative node representations on homophilic and heterophilic graphs. Then, we leverage a prototype-based approach to initialize parameters and contrastive learning for regularizing the distribution of node embeddings. Moreover, we apply self-training to extract valuable information from unlabeled nodes. Additionally, we adopt S \({}^{2}\) (scaling and shifting) transformation to learn transferable knowledge from diverse tasks. The results on real-world datasets show the superiority of Meta-GPS \(++\) . Our code is available here .

22 April 2025
Verified
Conference Paper
Open access
YLYonghao Liu
Yonghao Liu
MLMengyu Li
Mengyu Li
FGFausto Giunchiglia
Fausto Giunchiglia
LHLan Huang
Lan Huang
Ximing LiXiming Li
Ximing Li
RGRenchu Guan
Renchu Guan


1 November 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
MLMengyu Li
Mengyu Li
YLYonghao Liu
Yonghao Liu
Ximing LiXiming Li
Ximing Li
LHLan Huang
Lan Huang
FGFausto Giunchiglia
Fausto Giunchiglia
RGRenchu Guan
Renchu Guan