Depression Diagnosis and Analysis via Multimodal Multi-order Factor Fusion
This work addresses the challenge of improving accuracy and interpretability in automatic depression diagnosis, which is crucial for mental health care, but it appears incremental as it builds on existing multimodal approaches.
The paper tackled the problem of diagnosing depression by addressing limitations in existing multimodal learning methods, such as poor exploitation of high-order interactions and weak interpretability, and proposed a multimodal multi-order factor fusion method that achieved significantly better performance on datasets like E-DAIC-WOZ and CMDC.
Depression is a leading cause of death worldwide, and the diagnosis of depression is nontrivial. Multimodal learning is a popular solution for automatic diagnosis of depression, and the existing works suffer two main drawbacks: 1) the high-order interactions between different modalities can not be well exploited; and 2) interpretability of the models are weak. To remedy these drawbacks, we propose a multimodal multi-order factor fusion (MMFF) method. Our method can well exploit the high-order interactions between different modalities by extracting and assembling modality factors under the guide of a shared latent proxy. We conduct extensive experiments on two recent and popular datasets, E-DAIC-WOZ and CMDC, and the results show that our method achieve significantly better performance compared with other existing approaches. Besides, by analyzing the process of factor assembly, our model can intuitively show the contribution of each factor. This helps us understand the fusion mechanism.