# Learning to Rank for Active Learning via Multi-Task Bilevel Optimization

arXiv: https://arxiv.org/abs/2310.17044 · HTML: https://mlsanity.com/paper/2310.17044/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 75 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Meta-Learning with Implicit Gradients](https://mlsanity.com/paper/1909.04630/) (2019)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Bilevel Programming for Hyperparameter Optimization and Meta-Learning](https://mlsanity.com/paper/1806.04910/) (2018)
- [Gradient-based Hyperparameter Optimization through Reversible Learning](https://mlsanity.com/paper/1502.03492/) (2015)
- [Selection via Proxy: Efficient Data Selection for Deep Learning](https://mlsanity.com/paper/1906.11829/) (2019)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning](https://mlsanity.com/paper/2012.10630/) (2020)
- [Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration](https://mlsanity.com/paper/1705.09634/) (2017)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [On the Iteration Complexity of Hypergradient Computation](https://mlsanity.com/paper/2006.16218/) (2020)
- [Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets](https://mlsanity.com/paper/2202.02794/) (2022)
- [Batch Active Learning at Scale](https://mlsanity.com/paper/2107.14263/) (2021)
- [Assessing Generalization of SGD via Disagreement](https://mlsanity.com/paper/2106.13799/) (2021)
- [Deep Active Learning for Named Entity Recognition](https://mlsanity.com/paper/1707.05928/) (2017)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [Self-Supervised Generalisation with Meta Auxiliary Learning](https://mlsanity.com/paper/1901.08933/) (2019)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Learning how to Active Learn: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1708.02383/) (2017)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [LAVA: Data Valuation without Pre-Specified Learning Algorithms](https://mlsanity.com/paper/2305.00054/) (2023)
- [Active Learning Through a Covering Lens](https://mlsanity.com/paper/2205.11320/) (2022)

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

- [All models are wrong, some are useful: Model Selection with Limited Labels](https://mlsanity.com/paper/2410.13609/) (2024)
- [A Unified Evaluation Framework for Multi-Annotator Tendency Learning](https://mlsanity.com/paper/2508.10393/) (2025)
- [FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery](https://mlsanity.com/paper/2607.25276/) (2026)

## Abstract (arXiv)

Active learning is a promising paradigm to reduce the labeling cost by strategically requesting labels to improve model performance. However, existing active learning methods often rely on expensive acquisition function to compute, extensive modeling retraining and multiple rounds of interaction with annotators. To address these limitations, we propose a novel approach for active learning, which aims to select batches of unlabeled instances through a learned surrogate model for data acquisition. A key challenge in this approach is developing an acquisition function that generalizes well, as the history of data, which forms part of the utility function's input, grows over time. Our novel algorithmic contribution is a bilevel multi-task bilevel optimization framework that predicts the relative utility -- measured by the validation accuracy -- of different training sets, and ensures the learned acquisition function generalizes effectively. For cases where validation accuracy is expensive to evaluate, we introduce efficient interpolation-based surrogate models to estimate the utility function, reducing the evaluation cost. We demonstrate the performance of our approach through extensive experiments on standard active classification benchmarks. By employing our learned utility function, we show significant improvements over traditional techniques, paving the way for more efficient and effective utility maximization in active learning applications.