mlsanityData to 7 Oct 2026

A Method for Discovering Novel Classes in Tabular Data

arXiv 2209.01217 ↗First posted 2 Sep 2022cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes. While NCD has recently gained attention from the community, no framework has yet been proposed for heterogeneous tabular data, despite being a very common representation of data. In this paper, we propose TabularNCD, a new method for discovering novel classes in tabular data. We show a way to extract knowledge from already known classes to guide the discovery process of novel classes in the context of tabular data which contains heterogeneous variables. A part of this process is done by a new method for defining pseudo labels, and we follow recent findings in Multi-Task Learning to optimize a joint objective function. Our method demonstrates that NCD is not only applicable to images but also to heterogeneous tabular data. Extensive experiments are conducted to evaluate our method and demonstrate its effectiveness against 3 competitors on 7 diverse public classification datasets.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 2 Sep 2022.

Builds on

23 of 48 references.

References · 23

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  4. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  5. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  6. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  7. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  8. 2020Learning under Concept Drift: A Reviewcited by 470
  9. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  10. 2021Open-World Semi-Supervised Learningcited by 165
  11. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
  12. 2017Learning to cluster in order to transfer across domains and taskscited by 128
11 more
  1. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  2. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  3. 2021SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learningcited by 101
  4. 2019Multi-class Classification without Multi-class Labelscited by 100
  5. 2018Open-world Learning and Application to Product Classificationcited by 39
  6. 2021Meta Discovery: Learning to Discover Novel Classes given Very Limited Datacited by 30
  7. 2018Unseen Class Discovery in Open-world Classificationcited by 20
  8. 2020Open-World Class Discovery with Kernel Networkscited by 12
  9. 2020From Weakly Supervised Learning to Biquality Learning: an Introductioncited by 10
  10. 2019Multi-stage Deep Classifier Cascades for Open World Recognitioncited by 4
  11. 2020Text Classification with Novelty Detectioncited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 0; 2025: 1.

6 papers.

  1. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  2. 2025Category Discovery: An Open-World Perspectivecited by 5
  3. 2023An Interactive Interface for Novel Class Discovery in Tabular Datacited by 2
  4. 2023A Practical Approach to Novel Class Discovery in Tabular Datacited by 2
  5. 2023Detecting Novelties with Empty Classescited by 1
  6. 2022D'ecouvrir de nouvelles classes dans des donn'ees tabulairescited by 0