# Tree DNN: A Deep Container Network

arXiv: https://arxiv.org/abs/2212.03474 · HTML: https://mlsanity.com/paper/2212.03474/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 8 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 1 of 1)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)

## Abstract (arXiv)

Multi-Task Learning (MTL) has shown its importance at user products for fast training, data efficiency, reduced overfitting etc. MTL achieves it by sharing the network parameters and training a network for multiple tasks simultaneously. However, MTL does not provide the solution, if each task needs training from a different dataset. In order to solve the stated problem, we have proposed an architecture named TreeDNN along with it's training methodology. TreeDNN helps in training the model with multiple datasets simultaneously, where each branch of the tree may need a different training dataset. We have shown in the results that TreeDNN provides competitive performance with the advantage of reduced ROM requirement for parameter storage and increased responsiveness of the system by loading only specific branch at inference time.