[其他] ICML-GNNAutoScale Scalable and Expressive Graph Neural Networks via Histori ... [推广有奖]

1关注
167
粉丝

已卖：5680份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13312 个
通用积分: 718.1716
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 116269 点
帖子: 4686
精华: 0
在线时间: 16731 小时
注册时间: 2013-1-2
最后登录: 2026-1-21

楼主

Mujahida

发表于 2025-8-10 07:19:06 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

GNNAutoScale: Scalable and Expressive Graph Neural Networks
            via Historical Embeddings

         Matthias Fey 1 Jan Eric Lenssen 1 Frank Weichert 1 Jure Leskovec 2

         Abstract                While the full-gradient in a GNN is straightforward to com-
We present GNNAutoScale (GAS), a framework       pute, assuming one has access to all hidden node embed-
for scaling arbitrary message-passing GNNs to       dings in all layers, this is not feasible in large-s ...