mlsanityData to 7 Oct 2026

AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System

arXiv 2203.14683 ↗First posted 28 Mar 2022cs.IR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph embedding based retrieval has become one of the most popular techniques in the information retrieval community and search engine industry. The classical paradigm mainly relies on the flat Euclidean geometry. In recent years, hyperbolic (negative curvature) and spherical (positive curvature) representation methods have shown their superiority to capture hierarchical and cyclic data structures respectively. However, in industrial scenarios such as e-commerce sponsored search platforms, the large-scale heterogeneous query-item-advertisement interaction graphs often have multiple structures coexisting. Existing methods either only consider a single geometry space, or combine several spaces manually, which are incapable and inflexible to model the complexity and heterogeneity in the real scenario. To tackle this challenge, we present a web-scale Adaptive Mixed-Curvature ADvertisement retrieval system (AMCAD) to automatically capture the complex and heterogeneous graph structures in non-Euclidean spaces. Specifically, entities are represented in adaptive mixed-curvature spaces, where the types and curvatures of the subspaces are trained to be optimal combinations. Besides, an attentive edge-wise space projector is designed to model the similarities between heterogeneous nodes according to local graph structures and the relation types. Moreover, to deploy AMCAD in Taobao, one of the largest ecommerce platforms with hundreds of million users, we design an efficient two-layer online retrieval framework for the task of graph based advertisement retrieval. Extensive evaluations on real-world datasets and A/B tests on online traffic are conducted to illustrate the effectiveness of the proposed system.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 49 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

31 of 49 references.

References · 31

  1. 2017Graph Attention Networkscited by 8,854
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  4. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  6. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  7. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  8. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  9. 2015LINE: Large-scale Information Network Embeddingcited by 582
  10. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  11. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  12. 2018Hyperbolic Neural Networkscited by 393
19 more
  1. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  2. 2019Hyperbolic Graph Neural Networkscited by 244
  3. 2018Representation Tradeoffs for Hyperbolic Embeddingscited by 204
  4. 2020Low-Dimensional Hyperbolic Knowledge Graph Embeddingscited by 195
  5. 2018Hyperspherical Variational Auto-Encoderscited by 188
  6. 2020Embedding-based Retrieval in Facebook Searchcited by 155
  7. 2019Constant Curvature Graph Convolutional Networkscited by 106
  8. 2019Mixed-curvature Variational Autoencoderscited by 85
  9. 2018Spherical Latent Spaces for Stable Variational Autoencoderscited by 66
  10. 2020From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clusteringcited by 65
  11. 2020Graph Geometry Interaction Learningcited by 55
  12. 2019Spherical Text Embeddingcited by 49
  13. 2018HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systemscited by 47
  14. 2020DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completioncited by 30
  15. 2017Hyperbolic Representation Learning for Fast and Efficient Neural Question Answeringcited by 23
  16. 2019Scalable Hyperbolic Recommender Systemscited by 19
  17. 2020Price-aware Recommendation with Graph Convolutional Networkscited by 14
  18. 2020Deep Hierarchical Classification for Category Prediction in E-commerce Systemcited by 8
  19. 2020Are Hyperbolic Representations in Graphs Created Equal?cited by 4

Built on by

Cited by year

Citing papers per year: 2023: 4.

4 papers.

  1. 2023Exploring Data Geometry for Continual Learningcited by 14
  2. 2023Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifoldcited by 4
  3. 2023ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraintcited by 3
  4. 2023Enhancing Dynamic Image Advertising with Vision-Language Pre-trainingcited by 2