paper-with-me

홈 › Papers

Lifelong Graph Learning for Graph Summarization

2024-07-25 · Jonatan Frank, Marcel Hoffmann, Nicolas Lell, David Richerby, Ansgar Scherp

Summarizing web graphs is challenging due to the heterogeneity of the modeled information and its changes over time. We investigate the use of neural networks for lifelong graph summarization. Assuming we observe the web graph at a certain time, we train the networks to summarize graph vertices. We apply this trained network to summarize the vertices of the changed graph at the next point in time. Subsequently, we continue training and evaluating the network to perform lifelong graph summarization. We use the GNNs Graph-MLP and GraphSAINT, as well as an MLP baseline, to summarize the temporal graphs. We compare $1$-hop and $2$-hop summaries. We investigate the impact of reusing parameters from a previous snapshot by measuring the backward and forward transfer and the forgetting rate of the neural networks. Our extensive experiments on ten weekly snapshots of a web graph with over $100$M edges, sampled in 2012 and 2022, show that all networks predominantly use $1$-hop information to determine the summary, even when performing $2$-hop summarization. Due to the heterogeneity of web graphs, in some snapshots, the $2$-hop summary produces over ten times more vertex summaries than the $1$-hop summary. When using the network trained on the last snapshot from 2012 and applying it to the first snapshot of 2022, we observe a strong drop in accuracy. We attribute this drop over the ten-year time warp to the strongly increased heterogeneity of the web graph in 2022.

📄 PDF Abstract BibTeX arXiv:2407.18042

Code (1)

jofranky/lifelong-graph-summarization-with-neural-networks 공식 구현 pytorch

Tasks

AttributeGraph Learning

Methods 이 논문이 사용한 방법론

GraphSAINT Scalable method to train large scale GNN models via sampling small subgraphs.

Similar Papers 제목 키워드 기반

Bridging Graph Network to Lifelong Learning with Feature Interaction

2021-01-01 · Chen Wang, Yuheng Qiu, Sebastian Scherer

Graph neural networks (GNN) are powerful models for many graph-structured tasks. In this paper, we aim to bridge GNN to lifelong learning, which is to overcome the effect of ``catastrophic forgetting" for continuously le…

Graph ClassificationLifelong learningNode Classification

Lifelong Graph Learning

2020-09-01 · CVPR 2022 1 · Chen Wang, Yuheng Qiu, Dasong Gao, Sebastian Scherer

Graph neural networks (GNN) are powerful models for many graph-structured tasks. Existing models often assume that the complete structure of the graph is available during training. In practice, however, graph-structured …

Action RecognitionContinual LearningGraph ClassificationGraph Learning+3

Graph Lifelong Learning: A Survey

2022-02-22 · Falih Gozi Febrinanto, Feng Xia, Kristen Moore, Chandra Thapa 외

Graph learning is a popular approach for performing machine learning on graph-structured data. It has revolutionized the machine learning ability to model graph data to address downstream tasks. Its application is wide d…

Graph LearningLifelong learningRecommendation SystemsSurvey

Guidance Graph Optimization for Lifelong Multi-Agent Path Finding

2024-02-02 · Yulun Zhang, He Jiang, Varun Bhatt, Stefanos Nikolaidis 외

We study how to use guidance to improve the throughput of lifelong Multi-Agent Path Finding (MAPF). Previous studies have demonstrated that, while incorporating guidance, such as highways, can accelerate MAPF algorithms,…

Multi-Agent Path Finding

Lifelong Learning of Graph Neural Networks for Open-World Node Classification

2020-06-25 · Lukas Galke, Benedikt Franke, Tobias Zielke, Ansgar Scherp

Graph neural networks (GNNs) have emerged as the standard method for numerous tasks on graph-structured data such as node classification. However, real-world graphs are often evolving over time and even new classes may a…

Lifelong learningNode Classification