中文
相关论文

相关论文: Heuristic Methods are Good Teachers to Distill MLP…

200 篇论文

To bridge the gaps between powerful Graph Neural Networks (GNNs) and lightweight Multi-Layer Perceptron (MLPs), GNN-to-MLP Knowledge Distillation (KD) proposes to distill knowledge from a well-trained teacher GNN into a student MLP. In this…

机器学习 · 计算机科学 2024-07-23 Lirong Wu , Yunfan Liu , Haitao Lin , Yufei Huang , Stan Z. Li

Graph Neural Networks (GNNs) have shown exceptional performance in the task of link prediction. Despite their effectiveness, the high latency brought by non-trivial neighborhood data dependency limits GNNs in practical deployments.…

机器学习 · 计算机科学 2023-06-06 Zhichun Guo , William Shiao , Shichang Zhang , Yozen Liu , Nitesh V. Chawla , Neil Shah , Tong Zhao

Recent years have witnessed the great success of Graph Neural Networks (GNNs) in handling graph-related tasks. However, MLPs remain the primary workhorse for practical industrial applications due to their desirable inference efficiency and…

机器学习 · 计算机科学 2023-06-06 Lirong Wu , Haitao Lin , Yufei Huang , Tianyu Fan , Stan Z. Li

Heterogeneous Graph Neural Networks (HGNNs) have achieved promising results in various heterogeneous graph learning tasks, owing to their superiority in capturing the intricate relationships and diverse relational semantics inherent in…

机器学习 · 计算机科学 2025-07-15 Yunhui Liu , Xinyi Gao , Tieke He , Jianhua Zhao , Hongzhi Yin

Graph Neural Networks (GNNs) are popular for graph machine learning and have shown great results on wide node classification tasks. Yet, they are less popular for practical deployments in the industry owing to their scalability challenges…

机器学习 · 计算机科学 2022-03-24 Shichang Zhang , Yozen Liu , Yizhou Sun , Neil Shah

To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP. Despite their great…

机器学习 · 计算机科学 2023-06-12 Lirong Wu , Haitao Lin , Yufei Huang , Stan Z. Li

Multiplex graphs, with multiple edge types (graph views) among common nodes, provide richer structural semantics and better modeling capabilities. Multiplex Graph Neural Networks (MGNNs), typically comprising view-specific GNNs and a…

机器学习 · 计算机科学 2025-02-11 Yunhui Liu , Zhen Tao , Xiang Zhao , Jianhua Zhao , Tao Zheng , Tieke He

GNN-to-MLP (G2M) methods have emerged as a promising approach to accelerate Graph Neural Networks (GNNs) by distilling their knowledge into simpler Multi-Layer Perceptrons (MLPs). These methods bridge the gap between the expressive power of…

机器学习 · 计算机科学 2025-07-28 Weigang Lu , Ziyu Guan , Wei Zhao , Yaming Yang , Yujie Sun , Zheng Liang , Yibing Zhan , Dapeng Tao

Recent studies attempted to utilize multilayer perceptrons (MLPs) to solve semisupervised node classification on graphs, by training a student MLP by knowledge distillation from a teacher graph neural network (GNN). While previous studies…

机器学习 · 计算机科学 2023-11-30 Yong-Min Shin , Won-Yong Shin

Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active distillation reduces these costs by querying an LLM oracle to train compact discriminative…

人工智能 · 计算机科学 2026-04-01 Ziyang Yu , Liang Zhao

Graph Neural Networks (GNNs) have revolutionized graph-based machine learning, but their heavy computational demands pose challenges for latency-sensitive edge devices in practical industrial applications. In response, a new wave of…

机器学习 · 计算机科学 2024-05-24 Weigang Lu , Ziyu Guan , Wei Zhao , Yaming Yang

Graph Neural Networks (GNNs) are the go-to model for graph data analysis. However, GNNs rely on two key operations - aggregation and update, which can pose challenges for low-latency inference tasks or resource-constrained scenarios. Simple…

机器学习 · 计算机科学 2026-01-14 Amir Eskandari , Aman Anand , Elyas Rashno , Farhana Zulkernine

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial…

机器学习 · 计算机科学 2024-03-07 Lirong Wu , Haitao Lin , Zhangyang Gao , Guojiang Zhao , Stan Z. Li

Recent studies attempted to utilize multilayer perceptrons (MLPs) to solve semi-supervised node classification on graphs, by training a student MLP by knowledge distillation (KD) from a teacher graph neural network (GNN). While previous…

机器学习 · 计算机科学 2023-11-21 Yong-Min Shin , Won-Yong Shin

Hypergraph Neural Networks (HGNNs) have recently attracted much attention and exhibited satisfactory performance due to their superiority in high-order correlation modeling. However, it is noticed that the high-order modeling capability of…

机器学习 · 计算机科学 2024-02-20 Yifan Feng , Yihe Luo , Shihui Ying , Yue Gao

How can we learn effective node representations on textual graphs? Graph Neural Networks (GNNs) that use Language Models (LMs) to encode textual information of graphs achieve state-of-the-art performance in many node classification tasks.…

The message-passing mechanism helps Graph Neural Networks (GNNs) achieve remarkable results on various node classification tasks. Nevertheless, the recursive nodes fetching and aggregation in message-passing cause inference latency when…

机器学习 · 计算机科学 2022-10-19 Jie Chen , Shouzhen Chen , Mingyuan Bai , Junbin Gao , Junping Zhang , Jian Pu

For large-scale applications, there is growing interest in replacing Graph Neural Networks (GNNs) with lightweight Multi-Layer Perceptrons (MLPs) via knowledge distillation. However, distilling GNNs for self-supervised graph representation…

机器学习 · 计算机科学 2025-10-07 Seong Jin Ahn , Myoung-Ho Kim

Distilling high-accuracy Graph Neural Networks (GNNs) to low-latency multilayer perceptions (MLPs) on graph tasks has become a hot research topic. However, conventional MLP learning relies almost exclusively on graph nodes and fails to…

机器学习 · 计算机科学 2024-12-10 Taiqiang Wu , Zhe Zhao , Jiahao Wang , Xingyu Bai , Lei Wang , Ngai Wong , Yujiu Yang

Recent years have witnessed great success in handling graph-related tasks with Graph Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial…

机器学习 · 计算机科学 2023-06-06 Lirong Wu , Jun Xia , Haitao Lin , Zhangyang Gao , Zicheng Liu , Guojiang Zhao , Stan Z. Li
‹ 上一页 1 2 3 10 下一页 ›