arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.09128cs.LGcs.SI
收藏

基于可微深度量化的半监督网络嵌入

Semi-supervised Network Embedding with Differentiable Deep Quantisation

Monash University(莫纳什大学);University of Electronic Science and Technology of China(电子科技大学)

Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li

摘要:

学习网络的准确低维嵌入是一项至关重要的任务,因为它有助于许多下游网络分析任务。对于大型网络,经过训练的嵌入通常需要大量的空间来存储,这使得存储和处理成为一个挑战。基于我们以前在半监督网络嵌入方面的工作,我们开发了d-SNEQ,这是一种用于网络嵌入的基于DNN的可微量化方法。d-SNEQ结合了秩损失以使学习的量化码具有丰富的高阶信息,并且能够大幅压缩训练嵌入的大小,从而减少存储占用并加快检索速度。我们还提出了一个新的评价指标,路径预测,公平和更直接地评估模型的性能上的高阶信息的保存。我们对四个具有不同特征的真实网络的评估表明,d-SNEQ在链接预测、路径预测、节点分类和节点推荐方面优于许多最先进的嵌入方法,同时具有更高的空间和时间效率。

英文摘要:

Learning accurate low-dimensional embeddings for a network is a crucial task as it facilitates many downstream network analytics tasks. For large networks, the trained embeddings often require a significant amount of space to store, making storage and processing a challenge. Building on our previous work on semi-supervised network embedding, we develop d-SNEQ, a differentiable DNN-based quantisation method for network embedding. d-SNEQ incorporates a rank loss to equip the learned quantisation codes with rich high-order information and is able to substantially compress the size of trained embeddings, thus reducing storage footprint and accelerating retrieval speed. We also propose a new evaluation metric, path prediction, to fairly and more directly evaluate model performance on the preservation of high-order information. Our evaluation on four real-world networks of diverse characteristics shows that d-SNEQ outperforms a number of state-of-the-art embedding methods in link prediction, path prediction, node classification, and node recommendation while being far more space- and time-efficient.

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。

↑