mlsanityData to 7 Oct 2026

Inferring Networks of Substitutable and Complementary Products

arXiv 1506.08839 ↗First posted 29 Jun 2015cs.SI cs.IRcited by 91

Not on the map. Why?

Abstract (arXiv)

In a modern recommender system, it is important to understand how products relate to each other. For example, while a user is looking for mobile phones, it might make sense to recommend other phones, but once they buy a phone, we might instead want to recommend batteries, cases, or chargers. These two types of recommendations are referred to as substitutes and complements: substitutes are products that can be purchased instead of each other, while complements are products that can be purchased in addition to each other. Here we develop a method to infer networks of substitutable and complementary products. We formulate this as a supervised link prediction task, where we learn the semantics of substitutes and complements from data associated with products. The primary source of data we use is the text of product reviews, though our method also makes use of features such as ratings, specifications, prices, and brands. Methodologically, we build topic models that are trained to automatically discover topics from text that are successful at predicting and explaining such relationships. Experimentally, we evaluate our system on the Amazon product catalog, a large dataset consisting of 9 million products, 237 million links, and 144 million reviews.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 21; 2023: 18; 2024: 12; 2025: 16; 2026: 10.

91 papers.

Sort:

By area:

  1. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
  2. 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representationscited by 131
  3. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  4. 2022Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Searchcited by 58
  5. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  6. 2022Task-Adaptive Few-shot Node Classificationcited by 43
  7. 2021Sampling methods for efficient training of graph convolutional networks: A surveycited by 40
  8. 2021Graph Few-shot Class-incremental Learningcited by 40
  9. 2022Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Codingcited by 40
  10. 2022Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalizationcited by 35
  11. 2021Knowledge Enhanced Pretrained Language Models: A Compreshensive Surveycited by 33
  12. 2022Graph Lifelong Learning: A Surveycited by 30
38 more
  1. 2023GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentationcited by 29
  2. 2022Transductive Linear Probing: A Novel Framework for Few-Shot Node Classificationcited by 24
  3. 2022Evaluation Methods and Measures for Causal Learning Algorithmscited by 23
  4. 2022Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learningcited by 19
  5. 2024Language Representations Can be What Recommenders Need: Findings and Potentialscited by 18
  6. 2021Graph Neural Networks: Methods, Applications, and Opportunitiescited by 16
  7. 2022Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendationcited by 16
  8. 2023Enhancing Graph Transformers with Hierarchical Distance Structural Encodingcited by 16
  9. 2022On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classificationcited by 15
  10. 2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
  11. 2023Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Trainingcited by 12
  12. 2022Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcitycited by 11
  13. 2023Improving Generalizability of Graph Anomaly Detection Models via Data Augmentationcited by 11
  14. 2024Node Identifiers: Compact, Discrete Representations for Efficient Graph Learningcited by 10
  15. 2021Cleora: A Simple, Strong and Scalable Graph Embedding Schemecited by 8
  16. 2021Comparative Explanations of Recommendationscited by 8
  17. 2022BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learningcited by 8
  18. 2023Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalizationcited by 8
  19. 2023Task-Equivariant Graph Few-shot Learningcited by 8
  20. 2023PathMLP: Smooth Path Towards High-order Homophilycited by 8
  21. 2021End-to-End Conversational Search for Online Shopping with Utterance Transfercited by 7
  22. 2022A Survey on Extreme Multi-label Learningcited by 7
  23. 2024Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Trainingcited by 7
  24. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
  25. 2023Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolboxcited by 6
  26. 2023Generalized test utilities for long-tail performance in extreme multi-label classificationcited by 6
  27. 2022Towards High-Order Complementary Recommendation via Logical Reasoning Networkcited by 5
  28. 2023Semi-supervised Adversarial Learning for Complementary Item Recommendationcited by 5
  29. 2023CCGen: Explainable Complementary Concept Generation in E-Commercecited by 5
  30. 2023Towards Memory-Efficient Training for Extremely Large Output Spaces -- Learning with 500k Labels on a Single Commodity GPUcited by 5
  31. 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
  32. 2021"Are you sure?": Preliminary Insights from Scaling Product Comparisons to Multiple Shopscited by 4
  33. 2022A Transformer-Based Substitute Recommendation Model Incorporating Weakly Supervised Customer Behavior Datacited by 4
  34. 2024Consistent algorithms for multi-label classification with macro-at-k metricscited by 4
  35. 2025CIMAGE: Exploiting the Conditional Independence in Masked Graph Auto-encoderscited by 4
  36. 2021Augmenting the User-Item Graph with Textual Similarity Modelscited by 3
  37. 2021Speeding-up One-vs-All Training for Extreme Classification via Smart Initializationcited by 3
  38. 2021Inferring Substitutable and Complementary Products with Knowledge-Aware Path Reasoning based on Dynamic Policy Networkcited by 3

50 most cited of 91 All 91 (JSON)