Yufei He

Yufei He

Auto-generated profile, based on publicly available information

Yufei He

National University of Singapore, Singapore, Singapore

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
30 April 2023
Verified
Conference Paper
Open access
ZHZhenyu Hou
Zhenyu Hou
YHYufei He
Yufei He
YCYukuo Cen
Yukuo Cen
XLXiao Liu
Xiao Liu
YDYuxiao Dong
Yuxiao Dong
JTJie Tang
Jie Tang
Graph self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label scarcity in real-world graph data. Among both sets of graph SSL techniques, the masked graph autoencoders (e.g., GraphMAE)—one type of generative methods—have recently produced promising results. The idea behind this is to reconstruct the node features (or structures)—that are randomly masked from the input—with the autoencoder architecture. However, the performance of masked feature reconstruction naturally relies on the discriminability of the input features and is usually vulnerable to disturbance in the features. In this paper, we present a masked self-supervised learning framework1 GraphMAE2 with the goal of overcoming this issue. The idea is to impose regularization on feature reconstruction for graph SSL. Specifically, we design the strategies of multi-view random re-mask decoding and latent representation prediction to regularize the feature reconstruction. The multi-view random re-mask decoding is to introduce randomness into reconstruction in the feature space, while the latent representation prediction is to enforce the reconstruction in the embedding space. Extensive experiments show that GraphMAE2 can consistently generate top results on various public datasets, including at least 2.45% improvements over state-of-the-art baselines on ogbn-Papers100M with 111M nodes and 1.6B edges.


22 April 2025
Verified
Conference Paper
Open access
YHYufei He
Yufei He
YSYuan Sui
Yuan Sui
XHXiaoxin He
Xiaoxin He
YLYue Liu
Yue Liu
YSYifei Sun
Yifei Sun
BHBryan Hooi
Bryan Hooi

9 June 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YLYue Liu
Yue Liu
JWJiaying Wu
Jiaying Wu
YHYufei He
Yufei He
RGRuihan Gong
Ruihan Gong
JXJun Xia
Jun Xia
Keqin LiKeqin Li
Keqin Li
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in solving complex tasks. However, their deliberative reasoning process leads to inefficiencies in token usage, memory consumption, and inference time. Thus, this survey provides a review of efficient inference methods designed specifically for LRMs, focusing on mitigating token inefficiency while preserving the reasoning quality. The overview structure of this paper is shown in Figure 1. First, we introduce a taxonomy to group the recent methods into two main categories: (a) explicit compact Chain-of-Thought (CoT), which reduces tokens while keeping the explicit reasoning structure, and (b) implicit latent CoT, which encodes reasoning steps within hidden representations instead of explicit tokens. Meanwhile, we discuss their strengths and weaknesses. Then, we conduct empirical analyses on existing methods from reasoning scenarios, object functions, and performance & efficiency aspects. Besides, we present open challenges in this field, including human-centric controllable reasoning, trade-off between interpretability and efficiency of reasoning, ensuring the safety of efficient reasoning, and broader applications of efficient reasoning. In addition, we highlight key insights for enhancing LRMs' inference efficiency via techniques such as model merging, new architectures, and agent routers. We hope this work serves as a valuable guide, helping researchers overcome challenges in this vibrant field. A collection of efficient reasoning methods for LRMs (papers and codes) is provided at this link: https://github.com/yueliu1999/Awesome-Efficient-Inference-for-LRMs.

13 November 2025 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YHYufei He
Yufei He
ZHZhenyu Hou
Zhenyu Hou
YCYukuo Cen
Yukuo Cen
JHJun Hu
Jun Hu
FHFeng He
Feng He
BHBryan Hooi
Bryan Hooi
Graph pre-training has been concentrated on graph-level tasks involving small graphs (e.g., molecular graphs) or learning node representations on a fixed graph. Extending graph pre-trained models to web-scale graphs with billions of nodes in industrial scenarios, while avoiding negative transfer across graphs or tasks, remains a challenge. We aim to develop a general graph pre-trained model with inductive ability that can make predictions for unseen new nodes and even new graphs. In this work, we introduce a scalable transformer-based graph pre-training framework called PGT (Pre-trained Graph Transformer). Based on the masked autoencoder architecture, we design two pre-training tasks: one for reconstructing node features and the other for reconstructing local structures. Unlike the original autoencoder architecture where the pre-trained decoder is discarded, we propose a novel strategy that utilizes the decoder for feature augmentation. Our framework, tested on the publicly available ogbn-papers100 M dataset with 111 million nodes and 1.6 billion edges, achieves state-of-the-art performance, showcasing scalability and efficiency. We have deployed our framework on Tencent’s online game data, confirming its capability to pre-train on real-world graphs with over 540 million nodes and 12 billion edges and to generalize effectively across diverse static and dynamic downstream tasks.

20 May 2026 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
XCXu Cheng
Xu Cheng
LYLiang Yao
Liang Yao
FHFeng He
Feng He
YCYukuo Cen
Yukuo Cen
YHYufei He
Yufei He
JTJie Tang
Jie Tang
Graph Neural Networks (GNNs) have emerged as powerful tools for various graph mining tasks, yet existing scalable solutions often struggle to balance execution efficiency with prediction accuracy. These difficulties stem from iterative message-passing techniques, which place significant computational demands and require extensive Graphics Processing Unit (GPU) memory, particularly when dealing with the neighbor explosion issue inherent in large-scale graphs. This article introduces a scalable, low-cost, flexible, and efficient GNN framework called LPS-GNN, which can perform representation learning on 100billion-edge graph with a single GPU in 10 hours and shows a 13.8% improvement in User Acquisition scenarios. We examine existing graph partitioning methods and design a superior graph partition algorithm named Label Propagation with METIS (LPMetis). In particular, LPMetis outperforms current state-of-the-art (SOTA) approaches on various evaluation metrics. In addition, our article proposes a subgraph augmentation strategy to enhance the model’s predictive performance. It exhibits excellent compatibility, allowing the entire framework to accommodate various GNN algorithms. Successfully deployed on the Tencent platform, LPS-GNN has been tested on public and real-world datasets, achieving performance lifts of 8.24% to 13.89% over SOTA models in online applications.