Multi-Scenario Ranking with Adaptive Feature Learning
This work addresses data sparsity and maintenance costs in recommendation and retrieval systems for industry applications, but it is incremental as it builds on existing multi-scenario learning paradigms.
The paper tackles the problem of multi-scenario ranking by proposing adaptive feature learning to refine discriminative feature representations in a scenario-aware manner, resulting in superior performance on the Alibaba search advertising platform as demonstrated by A/B tests.
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.