Multi-Scenario Ranking with Adaptive Feature Learning

TL;DR

This paper introduces a scenario-aware adaptive feature learning method for multi-scenario ranking, improving performance by tailoring feature importance to specific scenarios without complex network searches.

Contribution

It proposes a novel adaptive feature learning approach that enhances multi-scenario ranking by capturing scenario-specific feature importance, reducing the need for complex network structure search.

Findings

Improved ranking performance in multi-scenario settings.

Validated effectiveness through Alibaba platform A/B tests.

Demonstrated superiority over existing methods in production.

Abstract

Recently, Multi-Scenario Learning (MSL) is widely used in recommendation and retrieval systems in the industry because it facilitates transfer learning from different scenarios, mitigating data sparsity and reducing maintenance cost. These efforts produce different MSL paradigms by searching more optimal network structure, such as Auxiliary Network, Expert Network, and Multi-Tower Network. It is intuitive that different scenarios could hold their specific characteristics, activating the user's intents quite differently. In other words, different kinds of auxiliary features would bear varying importance under different scenarios. With more discriminative feature representations refined in a scenario-aware manner, better ranking performance could be easily obtained without expensive search for the optimal network structure. Unfortunately, this simple idea is mainly overlooked but much desired in real-world systems.Further analysis also validates the rationality of adaptive feature learning under a multi-scenario scheme. Moreover, our A/B test results on the Alibaba search advertising platform also demonstrate that Maria is superior in production environments.