Lune

SIGIR2021Top-tier venue

AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search

Chaozhuo Li, Bochen Pang, Yuming Liu, Hao Sun, Zheng Liu, Xing Xie, Tianqi Yang, Yanling Cui, Liangjie Zhang, Qi Zhang

Abstract

Sponsored search ads appear next to search results when people look for products and services on search engines. In recent years, they have become one of the most lucrative channels for marketing. As the fundamental basis of search ads, relevance modeling has attracted increasing attention due to the significant research challenges and tremendous practical value. Most existing approaches solely rely on the semantic information in the input query-ad pair, while the pure semantic information in the short ads data is not sufficient to fully identify user's search intents. Our motivation lies in incorporating the tremendous amount of unsupervised user behavior data from the historical search logs as the complementary graph to facilitate relevance modeling. In this paper, we extensively investigate how to naturally fuse the semantic textual information with the user behavior graph, and further propose three novel AdsGNN models to aggregate topological neighborhood from the perspectives of nodes, edges and tokens. Furthermore, two critical but rarely investigated problems, domain-specific pre-training and long-tail ads matching, are studied thoroughly. Empirically, we evaluate the AdsGNN models over the large industry dataset, and the experimental results of online/offline tests consistently demonstrate the superiority of our proposal.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

22 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph cites TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search
  • Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks cites TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search
  • Can GNN be Good Adapter for LLMs? cites GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers22

  1. GraphFormers: GNN-nested Transformers for Representation Learning on Textual GraphJunhan Yang, Zheng Liu, Shitao Xiao, Chaozhuo Li et al.NeurIPS 2021 · 262 citations
  2. Can GNN be Good Adapter for LLMs?Xuanwen Huang, Kaiqiao Han, Yang Yang, Dezheng Bao et al.WWW 2024 · 107 citations
  3. PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link PredictionShichang Zhang, Jiani Zhang, Xiang Song, Soji Adeshina et al.WWW 2023 · 59 citations
  4. Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsShitao Xiao, Zheng Liu, Weihao Han, Jianjin Zhang et al.SIGIR 2022 · 31 citations
  5. Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich NetworksBowen Jin, Yu Zhang, Qi Zhu, Jiawei HanKDD 2023 · 27 citations

Builds on1

  1. TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored SearchJason Zhu, Yanling Cui, Yuming Liu, Hao Sun et al.WWW 2021 · 99 citations

Related papers

  1. Leveraging Bidding Graphs for Advertiser-Aware Relevance Modeling in Sponsored SearchShuxian Bi, Chaozhuo Li, Xiao Han, Zheng Liu et al.EMNLP Findings 2021 · 7 citations
  2. AdsCVLR: Commercial Visual-Linguistic Representation Modeling in Sponsored SearchYongjie Zhu, Chunhui Han, Yuefeng Zhan, Bochen Pang et al.ACM MM 2022 · 4 citations
  3. Session Search with Pre-trained Graph Classification ModelShengjie Ma, Chong Chen, Jiaxin Mao, Qi Tian et al.SIGIR 2023 · 3 citations
  4. Learning from the Wisdom of Crowds: Exploiting Similar Sessions for Session SearchYuhang Ye, Zhonghua Li, Zhicheng Dou, Yutao Zhu et al.AAAI 2023 · 4 citations
  5. Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive ModelsYexing Xu, Wei Feng, Shen Zhang, Haohan Wang et al.CVPR 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines