标签归档:Graph model

Do Transformers Really Perform Bad for Graph Representation?

The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared to mainstream GNN variants. Therefore, it remains a mystery how Transformers could perform well for graph representation learning. In this paper, we solve this mystery by presenting Graphormer, which is built upon the standard Transformer architecture, and could attain excellent results on a broad range of graph representation learning tasks, especially on the recent OGB Large-Scale Challenge. Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model. To this end, we propose several simple yet effective structural encoding methods to help Graphormer better model graph-structured data. Besides, we mathematically characterize the expressive power of Graphormer and exhibit that with our ways of encoding the structural information of graphs, many popular GNN variants could be covered as the special cases of Graphormer.

https://arxiv.org/abs/2106.05234

Transformer架构已经成为自然语言处理和机器视觉等任务的主要模型之一。然而,它依然没有在图级的排行榜上展现出有竞争力的性能。所以,Transformer在图表示学习领域依然有需要探索的空间。在本文中,我们提出了Graphormer,这是一种基于标准Transformer的架构,可以实现在图表示学习任务上优秀的性能。模型的关键是如何有效的将图信息编码进架构中。最后,我们还提出了几个简单但有效的编码架构用于帮助Graphormer更好得建模图架构数据。另外,我们从数学角度分析了Graphormer架构的表达能力以及我们编码方式,许多受欢迎的GNN架构都可以转换成特殊形式的Graphormer.

Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation

Learning to Combine: Knowledge Aggregation for Multi-Source Domain  Adaptation | Papers With Code

Transferring knowledges learned from multiple source domains to target domain is a more practical and challenging task than conventional single-source domain adaptation. Furthermore, the increase of modalities brings more difficulty in aligning feature distributions among multiple domains. To mitigate these problems, we propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework
via exploring interactions among domains. In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjacent representations. On such basis, a graph model is learned to predict query samples under the guidance of correlated prototypes. In addition, we design a Relation Alignment Loss (RAL) to facilitate the consistency of categories’ relational interdependency and the compactness of features, which boosts
features’ intra-class invariance and inter-class separability. Comprehensive results on public benchmark datasets demonstrate that our approach outperforms existing methods with a remarkable margin.

相比于传统的单源领域适应,迁移来自于多个源领域的知识到目标领域是更实际和有挑战性的人物。进一步,模态的增加导致连结多个领域的特征分布更加困难。为了解决这些问题,我们提出了一个用于多源域适应的框架,通过探索域之间的交叉。本质上,一个知识图被构建于各种域的原型之上,去实现语义连接表示之间的信息传递。在以上基础之上,本在相关的原型的指导下一个图模型被学习,以预测查询样本。之外,我们设计了一个关系连接损失以保持类别之间相互依存的一致性和特征的紧密,这个损失可以促进特征的类内不变性和类间可区分性。

论文地址:https://arxiv.org/pdf/2007.08801.pdf

代码地址:https://github.com/ChrisAllenMing/LtC-MSDA