# Multi-objective Learning to Rank by Model Distillation

arXiv: https://arxiv.org/abs/2407.07181 · HTML: https://mlsanity.com/paper/2407.07181/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2024.

## Built on by (most cited first, 7 of 7)

- [COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework](https://mlsanity.com/paper/2410.08316/) (2024)
- [No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods](https://mlsanity.com/paper/2412.12092/) (2024)
- [BiListing: Modality Alignment for Listings](https://mlsanity.com/paper/2508.20396/) (2025)
- [Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments](https://mlsanity.com/paper/2602.23234/) (2026)
- [Representation Curriculum: Stagewise Training for Robust Ranking and Allocation](https://mlsanity.com/paper/2606.09891/) (2026)
- [JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling](https://mlsanity.com/paper/2606.19108/) (2026)
- [Interest Entanglement: The Hidden Barrier to Blind Super-Resolution Optimization](https://mlsanity.com/paper/2606.22353/) (2026)

## Abstract (arXiv)

In online marketplaces, search ranking's objective is not only to purchase or conversion (primary objective), but to also the purchase outcomes(secondary objectives), e.g. order cancellation(or return), review rating, customer service inquiries, platform long term growth. Multi-objective learning to rank has been widely studied to balance primary and secondary objectives. But traditional approaches in industry face some challenges including expensive parameter tuning leads to sub-optimal solution, suffering from imbalanced data sparsity issue, and being not compatible with ad-hoc objective. In this paper, we propose a distillation-based ranking solution for multi-objective ranking, which optimizes the end-to-end ranking system at Airbnb across multiple ranking models on different objectives along with various considerations to optimize training and serving efficiency to meet industry standards. We found it performs much better than traditional approaches, it doesn't only significantly increases primary objective by a large margin but also meet secondary objectives constraints and improve model stability. We also demonstrated the proposed system could be further simplified by model self-distillation. Besides this, we did additional simulations to show that this approach could also help us efficiently inject ad-hoc non-differentiable business objective into the ranking system while enabling us to balance our optimization objectives.