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 2407.05656cs.LGcs.CL
收藏

基于随机圆向量的多标签学习

Multi-label Learning with Random Circular Vectors

Hokkaido University(北海道大学);The University of Tokyo(东京大学);Nara Institute of Science and Technology(奈良科学技术研究所)

Ken Nishida, Kojiro Machi, Kazuma Onishi, Katsuhiko Hayashi, Hidetaka Kamigaito

AI总结:

针对极端多标签分类中深度神经网络因标签量大导致训练计算成本高的问题,提出用随机圆向量构建输出层与损失函数,在提升性能的同时最多缩减99%输出层规模。

摘要:

极端多标签分类(XMC)任务的目标是学习一个分类器,使其能够从大规模标签集中预测出与数据实例最相关的标签子集。尽管深度神经网络(DNN)已在XMC问题中展现出显著成效,但该任务仍颇具挑战性,因为需要处理数量庞大的输出标签,这会导致DNN训练的计算成本极高。本文通过探索随机圆向量的应用来解决这一问题,这类向量的每个分量都以复振幅形式表示。在我们的框架中,通过将最终输出层设为全连接层,直接预测编码了数据实例标签集合的低维圆向量,由此构建适用于XMC的DNN输出层与损失函数。我们在合成数据集上开展实验,验证了圆向量相比普通实值向量具备更优的标签编码能力与检索能力。随后我们在真实XMC数据集上进行实验,结果表明,与此前使用随机实值向量的模型相比,圆向量的这些优良特性可带来任务性能的显著提升,同时最多可将输出层规模缩减99%。

英文摘要:

The extreme multi-label classification~(XMC) task involves learning a classifier that can predict from a large label set the most relevant subset of labels for a data instance. While deep neural networks~(DNNs) have demonstrated remarkable success in XMC problems, the task is still challenging because it must deal with a large number of output labels, which make the DNN training computationally expensive. This paper addresses the issue by exploring the use of random circular vectors, where each vector component is represented as a complex amplitude. In our framework, we can develop an output layer and loss function of DNNs for XMC by representing the final output layer as a fully connected layer that directly predicts a low-dimensional circular vector encoding a set of labels for a data instance. We conducted experiments on synthetic datasets to verify that circular vectors have better label encoding capacity and retrieval ability than normal real-valued vectors. Then, we conducted experiments on actual XMC datasets and found that these appealing properties of circular vectors contribute to significant improvements in task performance compared with a previous model using random real-valued vectors, while reducing the size of the output layers by up to 99%.

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。

↑