mlsanityData to 7 Oct 2026

Enhancing Multi-field B2B Cloud Solution Matching via Contrastive Pre-training

arXiv 2402.07076 ↗First posted 11 Feb 2024cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Cloud solutions have gained significant popularity in the technology industry as they offer a combination of services and tools to tackle specific problems. However, despite their widespread use, the task of identifying appropriate company customers for a specific target solution to the sales team of a solution provider remains a complex business problem that existing matching systems have yet to adequately address. In this work, we study the B2B solution matching problem and identify two main challenges of this scenario: (1) the modeling of complex multi-field features and (2) the limited, incomplete, and sparse transaction data. To tackle these challenges, we propose a framework CAMA, which is built with a hierarchical multi-field matching structure as its backbone and supplemented by three data augmentation strategies and a contrastive pre-training objective to compensate for the imperfections in the available data. Through extensive experiments on a real-world dataset, we demonstrate that CAMA outperforms several strong baseline matching models significantly. Furthermore, we have deployed our matching framework on a system of Huawei Cloud. Our observations indicate an improvement of about 30% compared to the previous online model in terms of Conversion Rate (CVR), which demonstrates its great business value.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 56 references that are in the map. First posted on arXiv 11 Feb 2024.

Builds on

24 of 56 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  4. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
  5. 2016Wide & Deep Learning for Recommender Systemscited by 745
  6. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
  7. 2015Generating Sentences from a Continuous Spacecited by 607
  8. 2016A Decomposable Attention Model for Natural Language Inferencecited by 214
  9. 2016Enhanced LSTM for Natural Language Inferencecited by 199
  10. 2015Semi-supervised Sequence Learningcited by 198
  11. 2020Deep Entity Matching with Pre-Trained Language Modelscited by 143
  12. 2021GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graphcited by 143
12 more
  1. 2022Towards Universal Sequence Representation Learning for Recommender Systemscited by 120
  2. 2019Neural News Recommendation with Attentive Multi-View Learningcited by 59
  3. 2015Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrievalcited by 54
  4. 2021TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Searchcited by 54
  5. 2020An Embedding Learning Framework for Numerical Features in CTR Predictioncited by 37
  6. 2020TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrievalcited by 24
  7. 2021Contrastive Learning of User Behavior Sequence for Context-Aware Document Rankingcited by 18
  8. 2021Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answeringcited by 8
  9. 2017Neural Ranking Models with Multiple Document Fieldscited by 7
  10. 2022MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Samplingcited by 4
  11. 2021New Hybrid Techniques for Business Recommender Systemscited by 1
  12. 2022CDSM: Cascaded Deep Semantic Matching on Textual Graphs Leveraging Ad-hoc Neighbor Selectioncited by 1

Built on by

Not cited yet.