mlsanityData to 7 Oct 2026

GANDALF: Gated Adaptive Network for Deep Automated Learning of Features

arXiv 2207.08548 ↗First posted 18 Jul 2022cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We propose a novel high-performance, interpretable, and parameter & computationally efficient deep learning architecture for tabular data, Gated Adaptive Network for Deep Automated Learning of Features (GANDALF). GANDALF relies on a new tabular processing unit with a gating mechanism and in-built feature selection called Gated Feature Learning Unit (GFLU) as a feature representation learning unit. We demonstrate that GANDALF outperforms or stays at-par with SOTA approaches like XGBoost, SAINT, FT-Transformers, etc. by experiments on multiple established public benchmarks. We have made available the code at github.com/manujosephv/pytorchtabular under MIT License.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 22 of its 49 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

22 of 49 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  5. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  7. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  8. 2016Language Modeling with Gated Convolutional Networkscited by 688
  9. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  10. 2017Convolutional Sequence to Sequence Learningcited by 550
  11. 2021Tabular Data: Deep Learning is Not All You Needcited by 530
  12. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
10 more
  1. 2016From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classificationcited by 337
  2. 2015Highway Networkscited by 257
  3. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
  4. 2017OpenML Benchmarking Suitescited by 169
  5. 2019Sparse Sequence-to-Sequence Modelscited by 167
  6. 2019Sanity Checks for Saliency Metricscited by 119
  7. 2021DANets: Deep Abstract Networks for Tabular Data Classification and Regressioncited by 50
  8. 2021PyTorch Tabular: A Framework for Deep Learning with Tabular Datacited by 20
  9. 2018Feature Selection using Stochastic Gatescited by 12
  10. 2020Feature Selection Using Batch-Wise Attenuation and Feature Mask Normalizationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 2; 2026: 1.

9 papers.

  1. 2023UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Sciencecited by 28
  2. 2024Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretrainingcited by 12
  3. 2024Fault Detection for agents on power grid topology optimization: A Comprehensive analysiscited by 2
  4. 2023An Epistemic and Aleatoric Decomposition of Arbitrariness to Constrain the Set of Good Modelscited by 1
  5. 2024TRACE: Transformer-based Risk Assessment for Clinical Evaluationcited by 1
  6. 2024Iterative Feature Exclusion Ranking for Deep Tabular Learningcited by 0
  7. 2025VirnyFlow: Optimizing ML Pipelines for Accuracy, Fairness, and Stability at Scalecited by 0
  8. 2025SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learningcited by 0
  9. 2026Structural Compositional Function Networks: Interpretable Functional Compositions for Tabular Discoverycited by 0