# Connectivity Learning in Multi-Branch Networks

arXiv: https://arxiv.org/abs/1709.09582 · HTML: https://mlsanity.com/paper/1709.09582/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2017.

## Built on by (most cited first, 3 of 3)

- [DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning](https://mlsanity.com/paper/2509.16105/) (2025)
- [Automotive Parts Assessment: Applying Real-time Instance-Segmentation Models to Identify Vehicle Parts](https://mlsanity.com/paper/2202.00884/) (2022)
- [Multi-Path Transformer is Better: A Case Study on Neural Machine Translation](https://mlsanity.com/paper/2305.05948/) (2023)

## Abstract (arXiv)

While much of the work in the design of convolutional networks over the last five years has revolved around the empirical investigation of the importance of depth, filter sizes, and number of feature channels, recent studies have shown that branching, i.e., splitting the computation along parallel but distinct threads and then aggregating their outputs, represents a new promising dimension for significant improvements in performance. To combat the complexity of design choices in multi-branch architectures, prior work has adopted simple strategies, such as a fixed branching factor, the same input being fed to all parallel branches, and an additive combination of the outputs produced by all branches at aggregation points. In this work we remove these predefined choices and propose an algorithm to learn the connections between branches in the network. Instead of being chosen a priori by the human designer, the multi-branch connectivity is learned simultaneously with the weights of the network by optimizing a single loss function defined with respect to the end task. We demonstrate our approach on the problem of multi-class image classification using three different datasets where it yields consistently higher accuracy compared to the state-of-the-art "ResNeXt" multi-branch network given the same learning capacity.