arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.10047cs.LGcs.AI
收藏

搜索深度图神经网络

Search For Deep Graph Neural Networks

Harbin Institute of Technology(哈尔滨工业大学);Peng Cheng Laboratory(鹏城实验室)

Guosheng Feng, Chunnan Wang, Hongzhi Wang

摘要:

目前面向GNN的NAS方法主要集中在寻找不同层次的聚合组件,这些组件具有浅而简单的架构,这受到“过平滑”问题的限制。为了进一步探索GNN架构的结构多样性和深度带来的好处,我们提出了一种具有新的两阶段搜索空间的GNN生成管道,其目的是以块方式自动生成高性能同时可转移的深度GNN模型。同时,为了缓解“过平滑”问题,我们在搜索空间中加入了多个灵活的剩余连接,并在基本GNN层中应用了恒等映射。对于搜索算法,我们使用深度q学习和epsilon贪婪探索策略和奖励重塑。在真实世界数据集上的大量实验表明,我们生成的GNN模型优于现有的手动设计和基于NAS的模型。

英文摘要:

Current GNN-oriented NAS methods focus on the search for different layer aggregate components with shallow and simple architectures, which are limited by the 'over-smooth' problem. To further explore the benefits from structural diversity and depth of GNN architectures, we propose a GNN generation pipeline with a novel two-stage search space, which aims at automatically generating high-performance while transferable deep GNN models in a block-wise manner. Meanwhile, to alleviate the 'over-smooth' problem, we incorporate multiple flexible residual connection in our search space and apply identity mapping in the basic GNN layers. For the search algorithm, we use deep-q-learning with epsilon-greedy exploration strategy and reward reshaping. Extensive experiments on real-world datasets show that our generated GNN models outperforms existing manually designed and NAS-based ones.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑