多热点紧凑型网络嵌入
Multi-Hot Compact Network Embedding
摘要：
网络嵌入作为一种很有前途的网络表示学习方法，能够支持后续的各种网络挖掘和分析任务，近年来引起了越来越多的研究兴趣。传统的方法为每个节点分配一个独立的连续向量，这将导致大型网络的巨大内存开销。在本文中，我们提出了一种新的多热紧凑嵌入策略，有效地减少内存成本，通过学习部分共享嵌入。该算法将一个节点嵌入向量由多个基向量组成，可以在保持相似数据表示能力的同时，显著减少连续向量的数量。具体来说，我们提出了一个MCNE模型，从预先学习的节点特征中学习紧凑嵌入。一个新的组件命名为压缩器集成到MCNE，以解决流行的反向传播优化不能通过离散样本传播的挑战。我们进一步提出了一个端到端模型MCNE $_{t}$，直接从输入网络学习紧凑嵌入。在三个真实网络数据集上对所提出的模型进行了实验评估，结果表明，在性能没有明显下降的情况下，所提出的模型可以节省约90%的网络嵌入的内存开销.
英文摘要：
Network embedding, as a promising way of the network representation learning, is capable of supporting various subsequent network mining and analysis tasks, and has attracted growing research interests recently. Traditional approaches assign each node with an independent continuous vector, which will cause huge memory overhead for large networks. In this paper we propose a novel multi-hot compact embedding strategy to effectively reduce memory cost by learning partially shared embeddings. The insight is that a node embedding vector is composed of several basis vectors, which can significantly reduce the number of continuous vectors while maintain similar data representation ability. Specifically, we propose a MCNE model to learn compact embeddings from pre-learned node features. A novel component named compressor is integrated into MCNE to tackle the challenge that popular back-propagation optimization cannot propagate through discrete samples. We further propose an end-to-end model MCNE$_{t}$ to learn compact embeddings from the input network directly. Empirically, we evaluate the proposed models over three real network datasets, and the results demonstrate that our proposals can save about 90\% of memory cost of network embeddings without significantly performance decline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
