# An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce

arXiv: https://arxiv.org/abs/2403.00923 · HTML: https://mlsanity.com/paper/2403.00923/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 53 references that are in the map.
- First posted on arXiv 1 Mar 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Fast WordPiece Tokenization](https://mlsanity.com/paper/2012.15524/) (2020)
- [Semantic Product Search](https://mlsanity.com/paper/1907.00937/) (2019)
- [Universal Graph Transformer Self-Attention Networks](https://mlsanity.com/paper/1909.11855/) (2019)
- [CoCoLM: COmplex COmmonsense Enhanced Language Model with Discourse Relations](https://mlsanity.com/paper/2012.15643/) (2020)
- [MergeDistill: Merging Pre-trained Language Models using Distillation](https://mlsanity.com/paper/2106.02834/) (2021)

## Built on by (most cited first, 6 of 6)

- [A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms](https://mlsanity.com/paper/2504.16420/) (2025)
- [LREF: A Novel LLM-based Relevance Framework for E-commerce](https://mlsanity.com/paper/2503.09223/) (2025)
- [You Are What You Bought: Generating Customer Personas for E-commerce Applications](https://mlsanity.com/paper/2504.17304/) (2025)
- [Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications](https://mlsanity.com/paper/2510.21131/) (2025)
- [A Scalable and Efficient Signal Integration System for Job Matching](https://mlsanity.com/paper/2507.09797/) (2025)
- [PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights](https://mlsanity.com/paper/2506.17314/) (2025)

## Abstract (arXiv)

The problem of search relevance in the E-commerce domain is a challenging one since it involves understanding the intent of a user's short nuanced query and matching it with the appropriate products in the catalog. This problem has traditionally been addressed using language models (LMs) and graph neural networks (GNNs) to capture semantic and inter-product behavior signals, respectively. However, the rapid development of new architectures has created a gap between research and the practical adoption of these techniques. Evaluating the generalizability of these models for deployment requires extensive experimentation on complex, real-world datasets, which can be non-trivial and expensive. Furthermore, such models often operate on latent space representations that are incomprehensible to humans, making it difficult to evaluate and compare the effectiveness of different models. This lack of interpretability hinders the development and adoption of new techniques in the field. To bridge this gap, we propose Plug and Play Graph LAnguage Model (PP-GLAM), an explainable ensemble of plug and play models. Our approach uses a modular framework with uniform data processing pipelines. It employs additive explanation metrics to independently decide whether to include (i) language model candidates, (ii) GNN model candidates, and (iii) inter-product behavioral signals. For the task of search relevance, we show that PP-GLAM outperforms several state-of-the-art baselines as well as a proprietary model on real-world multilingual, multi-regional e-commerce datasets. To promote better model comprehensibility and adoption, we also provide an analysis of the explainability and computational complexity of our model. We also provide the public codebase and provide a deployment strategy for practical implementation.