Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matching
Auteurs : Zongtao Liu, Bin Ma, Quan Liu, Jian Xu, Bo Zheng
Résumé scientifique
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.
Les articles autour de lui, par date et par proximité
Plus haut, c’est plus proche de cet article ; à gauche, c’est plus ancien. Les traits relient les articles proches entre eux : les groupes de traits sont des sous-thèmes. Sélectionnez un point pour voir pourquoi il est là. Retour au résumé de cet article
Les articles autour de celui-ci
Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.
Les articles les plus proches
-
A Dual Heterogeneous Graph Attention Network to Improve Long-Tail Performance for Shop Search in E-CommerceXichuan Niu, Bo-Fang Li, Chenliang Li et al. · 2020 · Knowledge Discovery and Data Mining · cité 79 fois · Pas encore résumé
Résumé scientifique
Shop search has become an increasingly important service provided by Taobao, the China's largest e-commerce platform. By using shop search, a user can easily identify the desired shop that provides a full-scale of relevant items matching his information need. With the tremendous growth of users and shops, shop search faces several unique challenging problems: 1) many shop names do not fully express what they sell, i.e., the semantic gap between user query and shop name; 2) due to the lack of user interactions, it is difficult to deliver a good search result for the long-tail queries and retrieve long-tail shops that are highly relevant to a query. To address these two key challenges, we reso…
-
Heterogeneous Ranking in Industrial-Scale Recommender Systems: A Case StudyDi Bai, Jin-Tao Liu, Zhenwei Tang et al. · 2026 · Proceedings of the 20th ACM Conference on Recommender Systems · Pas encore résumé
Résumé scientifique
Heterogeneous recommendation feeds present complex challenges that extend beyond those found in highly homogeneous environments (e.g., music-only or video-only closed-ecosystem platforms). In Google Discover, a unified feed integrates diverse content sourced from the decentralized open web, including web articles, long-form and short-form videos, user-generated content (UGC), and beyond. Different content types exhibit distinct feature densities and user interaction patterns. Building a unified ranking model that sustains high performance across such heterogeneity, while avoiding negative transfer or majority bias, remains a significant industrial challenge. This paper presents an end-to-end…
-
Keyword generation for search engine advertising using semantic similarity between termsV. Abhishek, Kartik Hosanagar · 2007 · International Conference on Evolutionary Computation · cité 124 fois · Pas encore résumé
-
Entity Representation Learning Through Onsite-Offsite Graph for Pinterest AdsJia-Yin Jin, Zhi-Meng Pan, Yang Tang et al. · 2025 · arXiv.org · preprint, non relu par les pairs · Pas encore résumé
Résumé scientifique
Graph Neural Networks (GNN) have been extensively applied to industry recommendation systems, as seen in models like GraphSage\cite{GraphSage}, TwHIM\cite{TwHIM}, LiGNN\cite{LiGNN} etc. In these works, graphs were constructed based on users'activities on the platforms, and various graph models were developed to effectively learn node embeddings. In addition to users'onsite activities, their offsite conversions are crucial for Ads models to capture their shopping interest. To better leverage offsite conversion data and explore the connection between onsite and offsite activities, we constructed a large-scale heterogeneous graph based on users'onsite ad interactions and opt-in offsite conversi…
-
Sequential Match Network: A New Architecture for Multi-turn Response Selection in Retrieval-based ChatbotsYu Wu, Wei Wu, Ming Zhou et al. · 2016 · Computation and Language · preprint, non relu par les pairs · cité 511 fois · Résumé IA disponible
Résumé scientifique
We study response selection for multi-turn conversation in retrieval based chatbots. Existing works either ignores relationships among utterances, or misses important information in context when matching a response with a highly abstract context vector finally. We propose a new session based matching model to address both problems. The model first matches a response with each utterance on multiple granularities, and distills important matching information from each pair as a vector with convolution and pooling operations. The vectors are then accumulated in a chronological order through a recurrent neural network (RNN) which models the relationships among the utterances. The final matching s…
-
Market-Aware Models for Efficient Cross-Market RecommendationSamarth Bhargav, Mohammad Aliannejadi, Evangelos Kanoulas · 2023 · Information Retrieval · cité 6 fois · Pas encore résumé
Résumé scientifique
We consider the cross-market recommendation (CMR) task, which involves recommendation in a low-resource target market using data from a richer, auxiliary source market. Prior work in CMR utilised meta-learning to improve recommendation performance in target markets; meta-learning however can be complex and resource intensive. In this paper, we propose market-aware (MA) models, which directly model a market via market embeddings instead of meta-learning across markets. These embeddings transform item representations into market-specific representations. Our experiments highlight the effectiveness and efficiency of MA models both in a pairwise setting with a single target-source market, as wel…
-
Bid keyword suggestion in sponsored search based on competitiveness and relevanceYing Zhang, Wei-Nan Zhang, Bin Gao et al. · 2014 · Information Processing & Management · cité 35 fois · Pas encore résumé
-
Advertising keyword suggestion based on concept hierarchyYi-Fan Chen, Gui-Rong Xue, Yong Yu · 2008 · Web Search and Data Mining · cité 110 fois · Pas encore résumé
Les travaux antérieurs sur lesquels il s’appuie
-
Learning deep structured semantic models for web search using clickthrough dataPo-Sen Huang, Xiao-Dong He, Jianfeng Gao et al. · 2013 · International Conference on Information and Knowledge Management · cité 2 533 fois · Pas encore résumé
-
Heterogeneous Graph Attention NetworkXiao Wang, Hou-Ye Ji, Chuan Shi et al. · 2019 · The Web Conference · cité 3 573 fois · Pas encore résumé
Résumé scientifique
Graph neural network, as a powerful graph representation technique based on deep learning, has shown superior performance and attracted considerable research interest. However, it has not been fully considered in graph neural network for heterogeneous graph which contains different types of nodes and links. The heterogeneity and rich semantic information bring great challenges for designing a graph neural network for heterogeneous graph. Recently, one of the most exciting advancements in deep learning is the attention mechanism, whose great potential has been well demonstrated in various areas. In this paper, we first propose a novel heterogeneous graph neural network based on the hierarchic…
-
Heterogeneous Graph Neural NetworkChuxu Zhang, Dong-Jin Song, Chao Huang et al. · 2019 · Knowledge Discovery and Data Mining · cité 1 749 fois · Pas encore résumé
Résumé scientifique
Representation learning in heterogeneous graphs aims to pursue a meaningful vector representation for each node so as to facilitate downstream applications such as link prediction, personalized recommendation, node classification, etc. This task, however, is challenging not only because of the demand to incorporate heterogeneous structural (graph) information consisting of multiple types of nodes and edges, but also due to the need for considering heterogeneous attributes or contents (e.g., text or image) associated with each node. Despite a substantial amount of effort has been made to homogeneous (or heterogeneous) graph embedding, attributed graph embedding as well as graph neural network…
-
Keyword Generation for Search Engine AdvertisingAmruta Joshi, R. Motwani · 2006 · Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06) · cité 119 fois · Pas encore résumé
-
Decoupled Graph Convolution Network for Inferring Substitutable and Complementary ItemsYiding Liu, Yulong Gu, Zhuo-Ye Ding et al. · 2020 · International Conference on Information and Knowledge Management · cité 55 fois · Pas encore résumé
Résumé scientifique
Inferring substitutable and complementary items is an important and fundamental concern for recommendation in e-commerce websites. However, the item relationships in real-world are usually heterogeneous, posing great challenges to conventional methods that can only deal with homogeneous relationships. More specifically, for this problem, there is a lack of in-depth investigation on 1) decoupling item semantics for modeling heterogeneous item relationships, and at the same time, 2) incorporating mutual influence between different relationships. To fill this gap, we propose a novel solution, namely Decoupled Graph Convolutional Network (DecGCN), to solve the problem of inferring substitutable …
Les articles qui le citent
-
LiGNN: Graph Neural Networks at LinkedInFedor Borisyuk, Shihai He, Yunbo Ouyang et al. · 2024 · Machine Learning · cité 47 fois · Pas encore résumé
Résumé scientifique
In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs) Framework. We share our insight on developing and deployment of GNNs at large scale at LinkedIn. We present a set of algorithmic improvements to the quality of GNN representation learning including temporal graph architectures with long term losses, effective cold start solutions via graph densification, ID embeddings and multi-hop neighbor sampling. We explain how we built and sped up by 7x our large-scale training on LinkedIn graphs with adaptive sampling of neighbors, grouping and slicing of training data batches, specialized shared-memory queue and local gradient optimization. We summarize our deployment…
-
HGL: Accelerating Heterogeneous GNN Training with Holistic Representation and OptimizationYun-Tao Gui, Yidi Wu, Han Yang et al. · 2022 · International Conference for High Performance Computing, Networking, Storage and Analysis · cité 13 fois · Pas encore résumé
Résumé scientifique
Graph neural networks (GNNs) have shown to significantly improve graph analytics. Existing systems for GNN training are primarily designed for homogeneous graphs. In industry, however, most graphs are actually heterogeneous in nature (i.e., having multiple types of nodes and edges). Existing systems train a heterogeneous GNN (HetGNN) as a composition of homogeneous GNN (HomoGNN) and thus suffer from critical limitations such as lack of memory optimization and limited operator parallelism. To address these limitations, we propose HGL - a heterogeneity-aware system for GNN training. At the core of HGL is an intermediate representation, called HIR, which provides a holistic representation for G…
-
Towards Hyper-Relevance in Marketing: Development of a Hybrid Cold-Start Recommender SystemL. Fernandes, V. Miguéis, Ivo Pereira et al. · 2023 · Applied Sciences · cité 6 fois · Pas encore résumé
Résumé scientifique
Recommender systems position themselves as powerful tools in the support of relevance and personalization, presenting remarkable potential in the area of marketing. The cold-start customer problematic presents a challenge within this topic, leading to the need of distinguishing user features and preferences based on a restricted set of transactional information. This paper proposes a hybrid recommender system that aims to leverage transactional and portfolio information as indicating characteristics of customer behaviour. Four independent systems are combined through a parallelised weighted hybrid design. The first individual system utilises the price, target age, and brand of each product t…
-
JTH: A Dataset for Evaluating Cold-Start and Temporal Dynamics in Job RecommendationJulien Romero, Y. Millet, Eric Behar · 2026 · Proceedings of the 20th ACM Conference on Recommender Systems · Pas encore résumé
Résumé scientifique
Job-matching platforms operate under brief and asymmetric lifetimes: vacancies close in weeks, while candidates are active for only a few days. Consequently, real-world recommenders must cope with pervasive cold start, extreme sparsity, and shifting temporal overlap. Existing public benchmarks lack the rich two-sided semantics and fine-grained timestamps needed to study these challenges. We present Job Tracking History (JTH), a seven-year corpus curated by professional recruiters. JTH pairs structured, LLM-enriched profiles for 38k candidates and 6k vacancies with day-level traces for 42k application trajectories, covering every stage from shortlist to offer. All data are de-identified via k…
-
Statistical Analysis of Design Aspects on Various Graph Embedding Learning ClassifiersA. Madhuri, T. Devi · 2023 · International Conference Computing Methodologies and Communication · cité 1 fois · Pas encore résumé
Résumé scientifique
Graphs representation learning is an emerging research topic. Graph representation learning generates vectors that capture immense graphs' structure and properties. The quality of graph representation vectors affects machine learning downward tasks like node categorization, edge estimation and anomaly detection. For efficient graph representation vectorization, both traditional graph embedding techniques and methods based on graph neural networks (GNN) have been described. These approaches work on “static & dynamic graphs”. In contrast to dynamic graphs which constantly adds new nodes and edges, static graphs consist of a single unchanging structure. This paper reviews traditional and GNN-ba…
Aller plus loin
Comment ces articles sont-ils trouvés ?
Nous comparons le titre et le résumé de cet article avec ceux de tous les articles résumés sur ce site, et avec les articles que Semantic Scholar recommande, ceux qu’il cite et ceux qui le citent (pour un article très cité, ses citations les plus récentes et, depuis OpenAlex, les plus citées). Parmi les travaux antérieurs et les suites, les articles qui s’utilisent en profondeur, une méthode qu’il utilise et les suites très citées remontent un peu. Les niveaux (très proche, proche, apparenté) viennent de la similarité des textes, pas d’un jugement de qualité ; * signale un article sans résumé, comparé par son titre. La phrase sous un article est écrite par une IA à partir des deux résumés : vérifiez-la dans les articles. Un article jugé hors sujet par trois lecteurs quitte la liste.
Mis à jour le 6 novembre 2026.