Automatic Expert Selection for Multi-Scenario and Multi-Task Search

05/28/2022
by   Xinyu Zou, et al.
0

Multi-scenario learning (MSL) enables a service provider to cater for users' fine-grained demands by separating services for different user sectors, e.g., by user's geographical region. Under each scenario there is a need to optimize multiple task-specific targets e.g., click through rate and conversion rate, known as multi-task learning (MTL). Recent solutions for MSL and MTL are mostly based on the multi-gate mixture-of-experts (MMoE) architecture. MMoE structure is typically static and its design requires domain-specific knowledge, making it less effective in handling both MSL and MTL. In this paper, we propose a novel Automatic Expert Selection framework for Multi-scenario and Multi-task search, named AESM^2. AESM^2 integrates both MSL and MTL into a unified framework with an automatic structure learning. Specifically, AESM^2 stacks multi-task layers over multi-scenario layers. This hierarchical design enables us to flexibly establish intrinsic connections between different scenarios, and at the same time also supports high-level feature extraction for different tasks. At each multi-scenario/multi-task layer, a novel expert selection algorithm is proposed to automatically identify scenario-/task-specific and shared experts for each input. Experiments over two real-world large-scale datasets demonstrate the effectiveness of AESM^2 over a battery of strong baselines. Online A/B test also shows substantial performance gain on multiple metrics. Currently, AESM^2 has been deployed online for serving major traffic.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 7

page 8

page 9

page 10

research
07/28/2023

TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts

Learning discriminative task-specific features simultaneously for multip...
research
09/16/2023

An Unified Search and Recommendation Foundation Model for Cold-Start Scenario

In modern commercial search engines and recommendation systems, data fro...
research
01/06/2023

Task Aware Feature Extraction Framework for Sequential Dependence Multi-Task Learning

Multi-task learning (MTL) has been successfully implemented in many real...
research
08/24/2023

Out of the Box Thinking: Improving Customer Lifetime Value Modelling via Expert Routing and Game Whale Detection

Customer lifetime value (LTV) prediction is essential for mobile game pu...
research
06/23/2023

OptMSM: Optimizing Multi-Scenario Modeling for Click-Through Rate Prediction

A large-scale industrial recommendation platform typically consists of m...
research
01/18/2022

Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling

Advertisers play an essential role in many e-commerce platforms like Tao...
research
06/29/2023

Multi-Scenario Ranking with Adaptive Feature Learning

Recently, Multi-Scenario Learning (MSL) is widely used in recommendation...

Please sign up or login with your details

Forgot password? Click here to reset