The world of e-commerce relies heavily on digital advertising, with platforms like Taobao and Amazon using it as a critical component. While consumer-focused issues such as click-through rate (CTR) and conversion rate (CVR) prediction have garnered attention in recent years, the advertiser side is becoming increasingly important. Sponsored search is a fundamental service that provides marketing tools to advertisers. The primary step in keyword recommendation for sponsored search is keyword matching which has been addressed by existing methods that model relevance based on a single type of relation among ads and keywords, such as query clicks or text similarity. However, these approaches neglect the rich heterogeneous interactions hidden behind them. To address this gap in knowledge, researchers face several challenges when it comes to keyword matching: how to learn enriched and robust embeddings from complex interactions among various types of objects; and how to conduct high-quality matching for new ads that usually lack sufficient data. To overcome these challenges, the authors developed HetMatch - a heterogeneous-graph-neural-network-based model for keyword matching - which has been deployed both online and offline at the core sponsored search platform of Alibaba Group. HetMatch extracts enriched and robust embeddings among rich relations by designing a hierarchical structure that fuses and enhances relevant neighborhood patterns both on the micro- and macro-levels. Additionally, by proposing a multi-view framework, HetMatch can involve more positive samples for cold-start ads. Experimental results on a large-scale industrial dataset as well as online AB tests exhibit the effectiveness of HetMatch. Overall, this paper highlights the importance of advertiser-side services in digital advertising platforms like Taobao and Amazon. It also sheds light on the challenges associated with keyword matching while introducing HetMatch - an effective solution that leverages heterogeneous graph neural networks to extract enriched embeddings from complex interactions among various types of objects.
E-commerce is buying and selling things online. Digital advertising means showing ads on the internet. Taobao and Amazon are websites that sell things online and use digital advertising to show their ads. Advertiser-side services help people who want to advertise their products online. Sponsored search is a tool that helps advertisers market their products. HetMatch is a new way of matching keywords for ads online, which helps advertisers find more customers. It uses a special computer program called a neural network to do this job better than before.
Understanding the Advertiser Side of Digital Advertising Platforms
Digital advertising is a critical component of e-commerce, with platforms like Taobao and Amazon relying heavily on it. While consumer-focused issues such as click-through rate (CTR) and conversion rate (CVR) prediction have been widely studied in recent years, the advertiser side has become increasingly important. Sponsored search is one of the fundamental services that provide marketing tools to advertisers, and keyword matching is an essential step in this process.
The Challenges of Keyword Matching
Existing methods for keyword matching model relevance based on a single type of relation among ads and keywords, such as query clicks or text similarity. However, these approaches neglect the rich heterogeneous interactions hidden behind them. To address this gap in knowledge, researchers face several challenges when it comes to keyword matching: how to learn enriched and robust embeddings from complex interactions among various types of objects; and how to conduct high-quality matching for new ads that usually lack sufficient data.
Introducing HetMatch
To overcome these challenges, researchers developed HetMatch - a heterogeneous graph neural network based model for keyword matching - which has been deployed both online and offline at the core sponsored search platform of Alibaba Group. HetMatch extracts enriched and robust embeddings among rich relations by designing a hierarchical structure that fuses and enhances relevant neighborhood patterns both on the micro-level (elements within each object) as well as macro-level (relations between different objects). Additionally, by proposing a multi-view framework, HetMatch can involve more positive samples for cold-start ads.
Experimental Results
Experimental results on a large scale industrial dataset as well as online AB tests exhibit the effectiveness of HetMatch compared to other existing methods for keyword matching. Overall, this paper highlights the importance of advertiser side services in digital advertising platforms like Taobao and Amazon while introducing an effective solution that leverages heterogeneous graph neural networks to extract enriched embeddings from complex interactions among various types of objects.
Digital advertising is a critical part of many e-commerce platforms such as Taobao and Amazon. While in recent years a lot of attention has been drawn to the consumer side including canonical problems like ctr/cvr prediction, the advertiser side, which directly serves advertisers by providing them with marketing tools, is now playing a more and more important role. When speaking of sponsored search, bid keyword recommendation is the fundamental service. This paper addresses the problem of keyword matching, the primary step of keyword recommendation. Existing methods for keyword matching merely consider modeling relevance based on a single type of relation among ads and keywords, such as query clicks or text similarity, which neglects rich heterogeneous interactions hidden behind them. To fill this gap, the keyword matching problem faces several challenges including: 1) how to learn enriched and robust embeddings from complex interactions among various types of objects; 2) how to conduct high-quality matching for new ads that usually lack sufficient data. To address these challenges, we develop a heterogeneous-graph-neural-network-based model for keyword matching named HetMatch, which has been deployed both online and offline at the core sponsored search platform of Alibaba Group. To extract enriched and robust embeddings among rich relations, we design a hierarchical structure to fuse and enhance the relevant neighborhood patterns both on the micro and the macro level. Moreover, by proposing a multi-view framework, the model is able to involve more positive samples for cold-start ads. Experimental results on a large-scale industrial dataset as well as online AB tests exhibit the effectiveness of HetMatch.
