AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevance
This addresses the problem of computational and maintenance inefficiencies in multi-task ads relevance modeling for ad platforms, though it appears incremental as it builds on existing attention mechanisms.
The paper tackles the challenge of modeling ad relevance across multiple ad types and scenarios by introducing a multi-faceted attention model that performs task-aware feature combination and cross-task interaction. The result is a single unified model that outperforms generalized DNN and task-specific models in various ad applications.
Ads relevance models are crucial in determining the relevance between user search queries and ad offers, often framed as a classification problem. The complexity of modeling increases significantly with multiple ad types and varying scenarios that exhibit both similarities and differences. In this work, we introduce a novel multi-faceted attention model that performs task aware feature combination and cross task interaction modeling. Our technique formulates the feature combination problem as "language" modeling with auto-regressive attentions across both feature and task dimensions. Specifically, we introduce a new dimension of task ID encoding for task representations, thereby enabling precise relevance modeling across diverse ad scenarios with substantial improvement in generality capability for unseen tasks. We demonstrate that our model not only effectively handles the increased computational and maintenance demands as scenarios proliferate, but also outperforms generalized DNN models and even task-specific models across a spectrum of ad applications using a single unified model.