# Retrieving Complex Tables with Multi-Granular Graph Representation Learning

arXiv: https://arxiv.org/abs/2105.01736 · HTML: https://mlsanity.com/paper/2105.01736/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 72 references that are in the map.
- First posted on arXiv 4 May 2021.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [Coordinate Descent Algorithms](https://mlsanity.com/paper/1502.04759/) (2015)
- [Open Question Answering over Tables and Text](https://mlsanity.com/paper/2010.10439/) (2020)
- [Pre-training Tasks for Embedding-based Large-scale Retrieval](https://mlsanity.com/paper/2002.03932/) (2020)
- [Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context](https://mlsanity.com/paper/2005.00589/) (2020)
- [SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning](https://mlsanity.com/paper/1711.04436/) (2017)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [Logical Natural Language Generation from Open-Domain Tables](https://mlsanity.com/paper/2004.10404/) (2020)
- [Joint Constrained Learning for Event-Event Relation Extraction](https://mlsanity.com/paper/2010.06727/) (2020)
- [Table-to-Text: Describing Table Region with Natural Language](https://mlsanity.com/paper/1805.11234/) (2018)

## Built on by (most cited first, 24 of 24)

- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [TransTab: Learning Transferable Tabular Transformers Across Tables](https://mlsanity.com/paper/2205.09328/) (2022)
- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks](https://mlsanity.com/paper/2201.09745/) (2022)
- [HYTREL: Hypergraph-enhanced Tabular Data Representation Learning](https://mlsanity.com/paper/2307.08623/) (2023)
- [Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning](https://mlsanity.com/paper/2205.03972/) (2022)
- [Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System](https://mlsanity.com/paper/2504.09207/) (2025)
- [FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining](https://mlsanity.com/paper/2109.07323/) (2021)
- [DeepJoin: Joinable Table Discovery with Pre-trained Language Models](https://mlsanity.com/paper/2212.07588/) (2022)
- [API-Assisted Code Generation for Question Answering on Varied Table Structures](https://mlsanity.com/paper/2310.14687/) (2023)
- [Table Retrieval May Not Necessitate Table-specific Model Design](https://mlsanity.com/paper/2205.09843/) (2022)
- [LakeBench: Benchmarks for Data Discovery over Data Lakes](https://mlsanity.com/paper/2307.04217/) (2023)
- [Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges](https://mlsanity.com/paper/2508.00217/) (2025)
- [Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation](https://mlsanity.com/paper/2504.14856/) (2025)
- [Empowering Tabular Data Preparation with Language Models: Why and How?](https://mlsanity.com/paper/2508.01556/) (2025)
- [Embeddings for Tabular Data: A Survey](https://mlsanity.com/paper/2302.11777/) (2023)
- [Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval](https://mlsanity.com/paper/2309.10506/) (2023)
- [Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats](https://mlsanity.com/paper/2406.17574/) (2024)
- [TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes](https://mlsanity.com/paper/2407.01619/) (2024)
- [HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval](https://mlsanity.com/paper/2603.02248/) (2026)
- [Semi-Structured Object Sequence Encoders](https://mlsanity.com/paper/2301.01015/) (2023)
- [FollowTable: A Benchmark for Instruction-Following Table Retrieval](https://mlsanity.com/paper/2605.00400/) (2026)
- [PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries](https://mlsanity.com/paper/2605.18199/) (2026)
- [Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method](https://mlsanity.com/paper/2605.18766/) (2026)

## Abstract (arXiv)

The task of natural language table retrieval (NLTR) seeks to retrieve semantically relevant tables based on natural language queries. Existing learning systems for this task often treat tables as plain text based on the assumption that tables are structured as dataframes. However, tables can have complex layouts which indicate diverse dependencies between subtable structures, such as nested headers. As a result, queries may refer to different spans of relevant content that is distributed across these structures. Moreover, such systems fail to generalize to novel scenarios beyond those seen in the training set. Prior methods are still distant from a generalizable solution to the NLTR problem, as they fall short in handling complex table layouts or queries over multiple granularities. To address these issues, we propose Graph-based Table Retrieval (GTR), a generalizable NLTR framework with multi-granular graph representation learning. In our framework, a table is first converted into a tabular graph, with cell nodes, row nodes and column nodes to capture content at different granularities. Then the tabular graph is input to a Graph Transformer model that can capture both table cell content and the layout structures. To enhance the robustness and generalizability of the model, we further incorporate a self-supervised pre-training task based on graph-context matching. Experimental results on two benchmarks show that our method leads to significant improvements over the current state-of-the-art systems. Further experiments demonstrate promising performance of our method on cross-dataset generalization, and enhanced capability of handling complex tables and fulfilling diverse query intents. Code and data are available at https://github.com/FeiWang96/GTR.