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 1811.04451stat.MLcs.LG
收藏

多源神经变分推断

Multi-Source Neural Variational Inference

Technical University of Munich(慕尼黑工业大学);Volkswagen Group(大众集团)

Richard Kurle, Stephan Günnemann, Patrick van der Smagt

摘要:

从多个信息源中学习是机器学习研究中的一个重要问题。关键的挑战是学习表示和制定推理方法,考虑到各种信息源的互补性和冗余性。在本文中,我们制定了一个变分自动编码器为基础的多源学习框架中,每个编码器的条件是一个不同的信息源。这使我们能够通过计算单个源的后验近似之间的发散度量来通过共享的潜变量将源关联起来。我们探索了各种选择来学习这些编码器,并将它们计算的信念整合到一致的后验近似中。我们在一个玩具数据集上可视化了学习到的信念,并评估了我们学习共享表示和结构化输出预测的方法,显示了为每个信息源学习单独编码器的权衡。此外,我们展示了如何冲突检测和冗余可以增加鲁棒性的推理在多源设置。

英文摘要:

Learning from multiple sources of information is an important problem in machine-learning research. The key challenges are learning representations and formulating inference methods that take into account the complementarity and redundancy of various information sources. In this paper we formulate a variational autoencoder based multi-source learning framework in which each encoder is conditioned on a different information source. This allows us to relate the sources via the shared latent variables by computing divergence measures between individual source's posterior approximations. We explore a variety of options to learn these encoders and to integrate the beliefs they compute into a consistent posterior approximation. We visualise learned beliefs on a toy dataset and evaluate our methods for learning shared representations and structured output prediction, showing trade-offs of learning separate encoders for each information source. Furthermore, we demonstrate how conflict detection and redundancy can increase robustness of inference in a multi-source setting.

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。

↑