Diffusion-based generative graph models have been proven effective in
generating high-quality small graphs. However, they need to be more scalable
for generating large graphs containing thousands of nodes desiring graph
statistics. In this work, we propose EDGE, a new diffusion-based generative
graph model that addresses generative tasks with large graphs. To improve
computation efficiency, we encourage graph sparsity by using a discrete
diffusion process that randomly removes edges at each time step and finally
obtains an empty graph. EDGE only focuses on a portion of nodes in the graph at
each denoising step. It makes much fewer edge predictions than previous
diffusion-based models. Moreover, EDGE admits explicitly modeling the node
degrees of the graphs, further improving the model performance. The empirical
study shows that EDGE is much more efficient than competing methods and can
generate large graphs with thousands of nodes. It also outperforms baseline
models in generation quality: graphs generated by our approach have more
similar graph statistics to those of the training graphs.

本文提出了一种名为 EDGE 的新型扩散生成图模型，通过在每个时间步骤随机删除边并最终获得空图的离散扩散过程，鼓励图结构的稀疏性，使其更有效率地生成包含上千节点的大型图，并明确将图中节点度数建模，与基线模型相比，生成的图像质量更高，具有更相似的图统计特征。

离散扩散模型下的高效度指导图生成

Efficient and Degree-Guided Graph Generation via Discrete Diffusion  Modeling

Link prediction is central to many real-world applications, but its
performance may be hampered when the graph of interest is sparse. To alleviate
issues caused by sparsity, we investigate a previously overlooked phenomenon:
in many cases, a densely connected, complementary graph can be found for the
original graph. The denser graph may share nodes with the original graph, which
offers a natural bridge for transferring meaningful knowledge. We identify this
setting as Graph Intersection-induced Transfer Learning (GITL), which is
motivated by practical applications in e-commerce or academic co-authorship
predictions.
We develop a framework to effectively leverage the structural prior in this
setting. We first create an intersection subgraph using the shared nodes
between the two graphs, then transfer knowledge from the source-enriched
intersection subgraph to the full target graph. In the second step, we consider
two approaches: a modified label propagation, and a multi-layer perceptron
(MLP) model in a teacher-student regime. Experimental results on proprietary
e-commerce datasets and open-source citation graphs show that the proposed
workflow outperforms existing transfer learning baselines that do not
explicitly utilize the intersection structure.

本文研究了图论中稀疏情况下 Link prediction 问题的解决方法，提出了使用 Intersection-induced Transfer Learning（GITL）框架中的 Multi-Layer Perceptron（MLP）模型，通过交叉节点的子图来解决该问题。实验证明，该框架优于现有的转移学习基线。

仅传递共享的内容：基于交互的图传输学习用于链接预测

You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction

The growing popularity of Graph Representation Learning (GRL) methods has
resulted in the development of a large number of models applied to a miscellany
of domains. Behind this diversity of domains, there is a strong heterogeneity
of graphs, making it difficult to estimate the expected performance of a model
on a new graph, especially when the graph has distinctive characteristics that
have not been encountered in the benchmark yet. To address this, we have
developed an experimental pipeline, to assess the impact of a given property on
the models performances. In this paper, we use this pipeline to study the
effect of two specificities encountered on banks transactional graphs resulting
from the partial view a bank has on all the individuals and transactions
carried out on the market. These specific features are graph sparsity and
asymmetric node information. This study demonstrates the robustness of GRL
methods to these distinctive characteristics. We believe that this work can
ease the evaluation of GRL methods to specific characteristics and foster the
development of such methods on transactional graphs.

本文使用实验管道研究了银行交易图表格稀疏性和不对称节点信息对图表格表示学习模型性能的影响，结果表明这些模型对于这些独特特征的鲁棒性。