# Task Addition in Multi-Task Learning by Geometrical Alignment

arXiv: https://arxiv.org/abs/2409.16645 · HTML: https://mlsanity.com/paper/2409.16645/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 10 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 4 of 4)

- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning](https://mlsanity.com/paper/2402.15017/) (2024)
- [Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks](https://mlsanity.com/paper/2310.06369/) (2023)
- [Multitask Extension of Geometrically Aligned Transfer Encoder](https://mlsanity.com/paper/2405.01974/) (2024)

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

- [Geometric Embedding Alignment via Curvature Matching in Transfer Learning](https://mlsanity.com/paper/2506.13015/) (2025)
- [Towards a Generalizable AI for Materials Discovery: Validation through Immersion Coolant Screening](https://mlsanity.com/paper/2510.23371/) (2025)

## Abstract (arXiv)

Training deep learning models on limited data while maintaining generalization is one of the fundamental challenges in molecular property prediction. One effective solution is transferring knowledge extracted from abundant datasets to those with scarce data. Recently, a novel algorithm called Geometrically Aligned Transfer Encoder (GATE) has been introduced, which uses soft parameter sharing by aligning the geometrical shapes of task-specific latent spaces. However, GATE faces limitations in scaling to multiple tasks due to computational costs. In this study, we propose a task addition approach for GATE to improve performance on target tasks with limited data while minimizing computational complexity. It is achieved through supervised multi-task pre-training on a large dataset, followed by the addition and training of task-specific modules for each target task. Our experiments demonstrate the superior performance of the task addition strategy for GATE over conventional multi-task methods, with comparable computational costs.