# Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task

arXiv: https://arxiv.org/abs/2201.02305 · HTML: https://mlsanity.com/paper/2201.02305/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 71 references that are in the map.
- First posted on arXiv 7 Jan 2022.

## Builds on (most cited first, 25 of 25)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning](https://mlsanity.com/paper/1911.12423/) (2019)
- [Multi-task self-supervised learning for Robust Speech Recognition](https://mlsanity.com/paper/2001.09239/) (2020)
- [NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction](https://mlsanity.com/paper/1801.08297/) (2018)
- [Understanding and Improving Information Transfer in Multi-Task Learning](https://mlsanity.com/paper/2005.00944/) (2020)
- [Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1812.09471/) (2018)
- [A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks](https://mlsanity.com/paper/1611.01587/) (2016)
- [Identifying beneficial task relations for multi-task learning in deep neural networks](https://mlsanity.com/paper/1702.08303/) (2017)
- [A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks](https://mlsanity.com/paper/1811.06031/) (2018)
- [Many Task Learning with Task Routing](https://mlsanity.com/paper/1903.12117/) (2019)
- [Learning Sparse Sharing Architectures for Multiple Tasks](https://mlsanity.com/paper/1911.05034/) (2019)
- [Latent Multi-task Architecture Learning](https://mlsanity.com/paper/1705.08142/) (2017)
- [Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Framework](https://mlsanity.com/paper/2011.06149/) (2020)
- [MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach](https://mlsanity.com/paper/2108.05060/) (2021)
- [Multi-Task Driven Feature Models for Thermal Infrared Tracking](https://mlsanity.com/paper/1911.11384/) (2019)
- [Multitask Learning with Single Gradient Step Update for Task Balancing](https://mlsanity.com/paper/2005.09910/) (2020)
- [Multi-Task Learning of Keyphrase Boundary Classification](https://mlsanity.com/paper/1704.00514/) (2017)
- [Deep Multi-Task Learning via Generalized Tensor Trace Norm](https://mlsanity.com/paper/2002.04799/) (2020)
- [Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network](https://mlsanity.com/paper/2002.04813/) (2020)
- [HydaLearn: Highly Dynamic Task Weighting for Multi-task Learning with Auxiliary Tasks](https://mlsanity.com/paper/2008.11643/) (2020)
- [Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs](https://mlsanity.com/paper/2101.12431/) (2021)

## Built on by (most cited first, 2 of 2)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Does Prior Data Matter? Exploring Joint Training in the Context of Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2503.10003/) (2025)

## Abstract (arXiv)

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same, thus they can be utilized for learning across the tasks. While almost rare works explore the scenario where each task only has a small amount of training samples, and their label sets are just partially overlapped or even not. Learning such MTs is more challenging because of less correlation information available among these tasks. For this, we propose a framework to learn these tasks by jointly leveraging both abundant information from a learnt auxiliary big task with sufficiently many classes to cover those of all these tasks and the information shared among those partially-overlapped tasks. In our implementation of using the same neural network architecture of the learnt auxiliary task to learn individual tasks, the key idea is to utilize available label information to adaptively prune the hidden layer neurons of the auxiliary network to construct corresponding network for each task, while accompanying a joint learning across individual tasks. Our experimental results demonstrate its effectiveness in comparison with the state-of-the-art approaches.