直播预告|UCLA 胡子牛博士——图神经网络及其自监督学习

点击蓝字

关注我们

AI TIME欢迎每一位AI爱好者的加入！

9月2日晚 7:30-8:30

AI TIME特别邀请了UCLA的胡子牛博士，为大家带来分享——图神经网络及其自监督学习

哔哩哔哩直播通道

★ 嘉宾简介 ★

胡子牛：

加利福尼亚大学洛杉矶分校第三年博士生，在Yizhou Sun教授实验室从事图机器学习的研究。

他的研究关注于对大规模异构图数据的图神经网络，以及运用图神经网络进行复杂的推理任务。

分享内容：

图神经网络及其自监督学习

报告简介：

Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. However, training GNNs usually requires abundant task-specific labeled data, which is often arduously expensive to obtain. One effective way to reduce the labeling effort is to pre-train an expressive GNN model on unlabeled data with self-supervision and then transfer the learned model to downstream tasks with only a few labels.

In this paper, we present the GPT-GNN framework to initialize GNNs by generative pre-training. GPT-GNN introduces a self-supervised attributed graph generation task to pre-train a GNN so that it can capture the structural and semantic properties of the graph. We factorize the likelihood of the graph generation into two components: 1) Attribute Generation and 2) Edge Generation. By modeling both components, GPT-GNN captures the inherent dependency between node attributes and graph structure during the generative process. Comprehensive experiments on the billion-scale Open Academic Graph and Amazon recommendation data demonstrate that GPT-GNN significantly outperforms state-of-the-art GNN models without pre-training by up to 9.1% across various downstream tasks.

今日视频推荐

直播结束后大家可以在群内进行提问，请添加“AI TIME小助手（微信号：AITIME_HY）”，回复“phd-3”，将拉您进“AI TIME PhD 交流群-3”！

AI TIME微信小助手

主        办：AI TIME 

合作媒体：学术头条、AI 数据派

合作伙伴：智谱·AI、中国工程院知领直播、学堂在线、学术头条、AMiner、biendata、 Ever链动

AI TIME欢迎AI领域学者投稿，期待大家剖析学科历史发展和前沿技术。针对热门话题，我们将邀请专家一起论道。同时，我们也长期招募优质的撰稿人，顶级的平台需要顶级的你，

请将简历等信息发至[email protected]！

微信联系:AITIME_HY

AI TIME是清华大学计算机系一群关注人工智能发展，并有思想情怀的青年学者们创办的圈子,旨在发扬科学思辨精神，邀请各界人士对人工智能理论、算法、场景、应用的本质问题进行探索，加强思想碰撞，打造一个知识分享的聚集地。

更多资讯请扫码关注

我知道你

在看

哦

~

点击 阅读原文 预约直播！