TY - JOUR AU - Kurle, Richard AU - Günnemann, Stephan AU - van der Smagt, Patrick PY - 2019/07/17 Y2 - 2024/03/29 TI - Multi-Source Neural Variational Inference JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 33 IS - 01 SE - AAAI Technical Track: Machine Learning DO - 10.1609/aaai.v33i01.33014114 UR - https://ojs.aaai.org/index.php/AAAI/article/view/4311 SP - 4114-4121 AB - <p>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.</p> ER -