# Semi-supervised classification by reaching consensus among modalities

arXiv: https://arxiv.org/abs/1805.09366 · HTML: https://mlsanity.com/paper/1805.09366/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

## Built on by (most cited first, 4 of 4)

- [Comparing Acoustic-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2106.01555/) (2021)
- [Situated Natural Language Explanations](https://mlsanity.com/paper/2308.14115/) (2023)
- [Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?](https://mlsanity.com/paper/2203.17110/) (2022)
- [Zero-Shot Multi-Lingual Speaker Verification in Clinical Trials](https://mlsanity.com/paper/2404.01981/) (2024)

## Abstract (arXiv)

Deep learning has demonstrated abilities to learn complex structures, but they can be restricted by available data. Recently, Consensus Networks (CNs) were proposed to alleviate data sparsity by utilizing features from multiple modalities, but they too have been limited by the size of labeled data. In this paper, we extend CN to Transductive Consensus Networks (TCNs), suitable for semi-supervised learning. In TCNs, different modalities of input are compressed into latent representations, which we encourage to become indistinguishable during iterative adversarial training. To understand TCNs two mechanisms, consensus and classification, we put forward its three variants in ablation studies on these mechanisms. To further investigate TCN models, we treat the latent representations as probability distributions and measure their similarities as the negative relative Jensen-Shannon divergences. We show that a consensus state beneficial for classification desires a stable but imperfect similarity between the representations. Overall, TCNs outperform or align with the best benchmark algorithms given 20 to 200 labeled samples on the Bank Marketing and the DementiaBank datasets.