Filters








6 Hits in 2.9 sec

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs [article]

Weihua Hu, Matthias Fey, Hongyu Ren, Maho Nakata, Yuxiao Dong, Jure Leskovec
2021 arXiv   pre-print
Here we present OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for facilitating the advancements in large-scale graph ML.  ...  Enabling effective and efficient machine learning (ML) over large-scale graph data (e.g., graphs with billions of edges) can have a great impact on both industrial and scientific applications.  ...  , Benjamin Braun and Hanjun Dai for providing helpful feedback on our baseline code, and the DGL Team for hosting our large datasets.  ... 
arXiv:2103.09430v3 fatcat:3xew2eoggfaohjzenvb7fo4ofy

Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021 [article]

Jianyu Cai, Jiajun Chen, Taoxing Pan, Zhanqiu Zhang, Jie Wang
2021 arXiv   pre-print
The OGB-LSC team presented OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for advancing the state-of-the-art in large-scale graph machine learning.  ...  Link prediction in large-scale knowledge graphs has gained increasing attention recently.  ...  ., 2020] is an effective method for mining rules from a large-scale knowledge graph, which employs a number of sophisticated pruning strategies and optimizations.  ... 
arXiv:2107.05476v1 fatcat:ccofzwx3ybaj7nioijnwvruqpu

On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction [article]

Edward Elson Kosasih, Joaquin Cabezas, Xavier Sumba, Piotr Bielak, Kamil Tagowski, Kelvin Idanwekhai, Benedict Aaron Tjandra, Arian Rokkum Jamasb
2021 arXiv   pre-print
In order to advance large-scale graph machine learning, the Open Graph Benchmark Large Scale Challenge (OGB-LSC) was proposed at the KDD Cup 2021.  ...  The PCQM4M-LSC dataset defines a molecular HOMO-LUMO property prediction task on about 3.8M graphs.  ...  OGB-LSC is a KDD 2021 Cup challenge.  ... 
arXiv:2106.15529v1 fatcat:e776x7ifgjhvrimrrqf53m53pu

First Place Solution of KDD Cup 2021 OGB Large-Scale Challenge Graph Prediction Track [article]

Chengxuan Ying, Mingqi Yang, Shuxin Zheng, Guolin Ke, Shengjie Luo, Tianle Cai, Chenglin Wu, Yuxin Wang, Yanming Shen, Di He
2021 arXiv   pre-print
In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our basic models.  ...  For final submission, we use a naive ensemble for these 18 models by taking average of their outputs.  ...  PCQM4M-LSC is a recent public dataset on the OGB Large-Scale Challenge (OGB-LSC) [Hu et al., 2021] , to encourage the development of state-of-the-art graph ML models.  ... 
arXiv:2106.08279v3 fatcat:o3zgosr2gjcm5ezomgihfpyybe

Large-scale graph representation learning with very deep GNNs and self-supervision [article]

Ravichandra Addanki, Peter W. Battaglia, David Budden, Andreea Deac, Jonathan Godwin, Thomas Keck, Wai Lok Sibon Li, Alvaro Sanchez-Gonzalez, Jacklynn Stott, Shantanu Thakoor, Petar Veličković
2021 arXiv   pre-print
Effectively and efficiently deploying graph neural networks (GNNs) at scale remains one of the most challenging aspects of graph representation learning.  ...  We entered the OGB-LSC with two large-scale GNNs: a deep transductive node classifier powered by bootstrapping, and a very deep (up to 50-layer) inductive graph regressor regularised by denoising objectives  ...  Accordingly, we have entered the recently proposed Open Graph Benchmark Large-Scale Challenge (OGB-LSC) [Hu et al., 2021] .  ... 
arXiv:2107.09422v1 fatcat:hch75eeggfbotduuytzvxowhku

A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs [article]

Charles Tapley Hoyt, Max Berrendorf, Mikhail Galkin, Volker Tresp, Benjamin M. Gyori
2022 arXiv   pre-print
The link prediction task on knowledge graphs without explicit negative triples in the training data motivates the usage of rank-based metrics.  ...  We finally propose several new rank-based metrics that are more easily interpreted and compared accompanied by a demonstration of their usage in a benchmarking of knowledge graph embedding models.  ...  of machine learning models like knowledge graph embedding models (KGEMs).  ... 
arXiv:2203.07544v2 fatcat:t2eea44tnvfx5ejcs3ix3yd22y