论文标题
贝斯：大规模知识图完成的平衡实体抽样和共享
BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completion
论文作者
论文摘要
我们将屡获殊荣的提交提交给OGB-LSC@Neurips 2022的Wikikg90MV2曲目。该任务是大规模知识图Wikikg90mv2的链接预测，由90m+节点和600m+边缘组成。我们的解决方案使用了$ 85 $知识图的多样集合，结合了五个不同的评分功能（Transe，Transh，Rotate，Distmult，Complex）和两个不同的损失函数（Log-Sigmoid，Sept-Sigmoid，SoftMax softmax跨透明镜）。使用BESS（平衡的实体采样和共享），在GraphCore Bow Pod $ _ {16} $上并行训练了每个单独的模型，这是一个基于工人之间平衡的集体通信的新的KGE培训和推理的新分发框架。我们的最终模型实现了0.2922的验证MRR，测试挑战MRR为0.2562，在比赛中赢得了第一名。该代码可在以下网址公开获取：https：//github.com/graphcore/distributed-kge-poplar/tree/2022-ogb-submission。
We present the award-winning submission to the WikiKG90Mv2 track of OGB-LSC@NeurIPS 2022. The task is link-prediction on the large-scale knowledge graph WikiKG90Mv2, consisting of 90M+ nodes and 600M+ edges. Our solution uses a diverse ensemble of $85$ Knowledge Graph Embedding models combining five different scoring functions (TransE, TransH, RotatE, DistMult, ComplEx) and two different loss functions (log-sigmoid, sampled softmax cross-entropy). Each individual model is trained in parallel on a Graphcore Bow Pod$_{16}$ using BESS (Balanced Entity Sampling and Sharing), a new distribution framework for KGE training and inference based on balanced collective communications between workers. Our final model achieves a validation MRR of 0.2922 and a test-challenge MRR of 0.2562, winning the first place in the competition. The code is publicly available at: https://github.com/graphcore/distributed-kge-poplar/tree/2022-ogb-submission.
