# Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences

arXiv: https://arxiv.org/abs/2407.08056 · HTML: https://mlsanity.com/paper/2407.08056/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 81 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 30 of 64)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)

## Built on by (most cited first, 13 of 13)

- [LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging](https://mlsanity.com/paper/2410.17146/) (2024)
- [PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model](https://mlsanity.com/paper/2505.06274/) (2025)
- [Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond](https://mlsanity.com/paper/2501.10945/) (2025)
- [LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch](https://mlsanity.com/paper/2409.02969/) (2024)
- [One Rank at a Time: Cascading Error Dynamics in Sequential Learning](https://mlsanity.com/paper/2505.22602/) (2025)
- [UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment](https://mlsanity.com/paper/2602.09538/) (2026)
- [Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning](https://mlsanity.com/paper/2504.11268/) (2025)
- [Towards Relaxed Multimodal Inputs for Gait-based Parkinson's Disease Assessment](https://mlsanity.com/paper/2510.15748/) (2025)
- [Model soups need only one ingredient](https://mlsanity.com/paper/2602.09689/) (2026)
- [MoIN: Mixture of Introvert Experts to Upcycle an LLM](https://mlsanity.com/paper/2410.09687/) (2024)
- [MAdam: Metric-Aware Multi-Objective Adam](https://mlsanity.com/paper/2606.03904/) (2026)
- [Multi-Objective Exploration and Preference Optimization via Mutual Information](https://mlsanity.com/paper/2607.01392/) (2026)
- [Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level](https://mlsanity.com/paper/2608.12704/) (2026)

## Abstract (arXiv)

Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary to traditional Multi-Task Learning (MTL) that optimizes for a single trade-off decided prior to training. However, recent PFL methodologies suffer from limited scalability, slow convergence, and excessive memory requirements, while exhibiting inconsistent mappings from preference to objective space. We introduce PaLoRA, a novel parameter-efficient method that addresses these limitations in two ways. First, we augment any neural network architecture with task-specific low-rank adapters and continuously parameterize the PF in their convex hull. Our approach steers the original model and the adapters towards learning general and task-specific features, respectively. Second, we propose a deterministic sampling schedule of preference vectors that reinforces this division of labor, enabling faster convergence and strengthening the validity of the mapping from preference to objective space throughout training. Our experiments show that PaLoRA outperforms state-of-the-art MTL and PFL baselines across various datasets, scales to large networks, reducing the memory overhead 23.8-31.7 times compared with competing PFL baselines in scene understanding benchmarks.