Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising (2021-05-31T00:00:00.000000Z)

TL;DR

A novel two-stage framework named Meta Hybrid Experts and Critics (MetaHeac) which has been deployed in WeChat Look-alike System and shows superior effectiveness for both content marketing campaigns in recommender systems and advertising campaigns in advertising platforms.

Abstract

In recommender systems and advertising platforms, marketers always want to deliver products, contents, or advertisements to potential audiences over media channels such as display, video, or social. Given a set of audiences or customers (seed users), the audience expansion technique (look-alike modeling) is a promising solution to identify more potential audiences, who are similar to the seed users and likely to finish the business goal of the target campaign. However, look-alike modeling faces two challenges: (1) In practice, a company could run hundreds of marketing campaigns to promote various contents within completely different categories every day, e.g., sports, politics, society. Thus, it is difficult to utilize a common method to expand audiences for all campaigns. (2) The seed set of a certain campaign could only cover limited users. Therefore, a customized approach based on such a seed set is likely to be overfitting. In this paper, to address these challenges, we propose a novel two-stage framework named Meta Hybrid Experts and Critics (MetaHeac) which has been deployed in WeChat Look-alike System. In the offline stage, a general model which can capture the relationships among various tasks is trained from a meta-learning perspective on all existing campaign tasks. In the online stage, for a new campaign, a customized model is learned with the given seed set based on the general model. According to both offline and online experiments, the proposed MetaHeac shows superior effectiveness for both content marketing campaigns in recommender systems and advertising campaigns in advertising platforms. Besides, MetaHeac has been successfully deployed in WeChat for the promotion of both contents and advertisements, leading to great improvement in the quality of marketing. The code has been available at https://github.com/easezyc/MetaHeac.

References35 items

Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising

Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks

Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users

Generalizing to Unseen Domains: A Survey on Domain Generalization

Two-Stage Audience Expansion for Financial Targeting in Marketing

Hubble: An Industrial System for Audience Expansion in Mobile Marketing

Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation

Multitask Mixture of Sequential Experts for User Activity Streams

Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering

Modeling Users’ Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection

Meta-Transfer Learning for Zero-Shot Super-Resolution

Adversarial Factorization Autoencoder for Look-alike Modeling

Finding Users Who Act Alike: Transfer Learning for Expanding Advertiser Audiences

Multiple Relational Attention Network for Multi-task Learning

Real-time Attention Based Look-alike Model for Recommender System

Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings

Meta-Transfer Learning for Few-Shot Learning

Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts

Learning to Generalize: Meta-Learning for Domain Generalization

Prototypical Networks for Few-shot Learning

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

A Sub-linear, Massive-scale Look-alike Audience Extension System A Massive-scale Look-alike Audience Extension

Score Look-Alike Audiences

Audience Expansion for Online Social Network Advertising

Effective Audience Extension in Online Advertising

Adam: A Method for Stochastic Optimization

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Focused matrix factorization for audience selection in display advertising

Learning to target: what works for behavioral targeting

A feature-pair-based associative classification approach to look-alike modeling for conversion-oriented user-targeting in tail campaigns

Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising