Tabular Data Contrastive Learning via Class-Conditioned and Feature-Correlation Based Augmentation
- URL: http://arxiv.org/abs/2404.17489v2
- Date: Tue, 30 Apr 2024 14:11:15 GMT
- Title: Tabular Data Contrastive Learning via Class-Conditioned and Feature-Correlation Based Augmentation
- Authors: Wei Cui, Rasa Hosseinzadeh, Junwei Ma, Tongzi Wu, Yi Sui, Keyvan Golestan,
- Abstract summary: Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space.
We propose a simple yet powerful improvement to this augmentation technique: corrupting tabular data conditioned on class identity.
Our code is available at https://github.com/willtop/Tabular-Class-Conditioned-SSL.
- Score: 9.593419261003692
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed success in image and natural language data, thanks to the domain-specific augmentation techniques that are both intuitive and effective. Nonetheless, in tabular domain, the predominant augmentation technique for creating views is through corrupting tabular entries via swapping values, which is not as sound or effective. We propose a simple yet powerful improvement to this augmentation technique: corrupting tabular data conditioned on class identity. Specifically, when corrupting a specific tabular entry from an anchor row, instead of randomly sampling a value in the same feature column from the entire table uniformly, we only sample from rows that are identified to be within the same class as the anchor row. We assume the semi-supervised learning setting, and adopt the pseudo labeling technique for obtaining class identities over all table rows. We also explore the novel idea of selecting features to be corrupted based on feature correlation structures. Extensive experiments show that the proposed approach consistently outperforms the conventional corruption method for tabular data classification tasks. Our code is available at https://github.com/willtop/Tabular-Class-Conditioned-SSL.
Related papers
- Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains [0.565395466029518]
We propose a novel pretext task based on the classical binning method.
The idea is straightforward: reconstructing the bin indices (either orders or classes) rather than the original values.
Our empirical investigations ascertain several advantages of binning.
arXiv Detail & Related papers (2024-05-13T01:23:14Z) - Training-Free Generalization on Heterogeneous Tabular Data via
Meta-Representation [67.30538142519067]
We propose Tabular data Pre-Training via Meta-representation (TabPTM)
A deep neural network is then trained to associate these meta-representations with dataset-specific classification confidences.
Experiments validate that TabPTM achieves promising performance in new datasets, even under few-shot scenarios.
arXiv Detail & Related papers (2023-10-31T18:03:54Z) - M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios [103.6153593636399]
We propose a vision-language prompt tuning method with mitigated label bias (M-Tuning)
It introduces open words from the WordNet to extend the range of words forming the prompt texts from only closed-set label words to more, and thus prompts are tuned in a simulated open-set scenario.
Our method achieves the best performance on datasets with various scales, and extensive ablation studies also validate its effectiveness.
arXiv Detail & Related papers (2023-03-09T09:05:47Z) - Distinguishability Calibration to In-Context Learning [31.375797763897104]
We propose a method to map a PLM-encoded embedding into a new metric space to guarantee the distinguishability of the resulting embeddings.
We also take the advantage of hyperbolic embeddings to capture the hierarchical relations among fine-grained class-associated token embedding.
arXiv Detail & Related papers (2023-02-13T09:15:00Z) - SubTab: Subsetting Features of Tabular Data for Self-Supervised
Representation Learning [5.5616364225463055]
We introduce a new framework, Subsetting features of Tabular data (SubTab)
In this paper, we introduce a new framework, Subsetting features of Tabular data (SubTab)
We argue that reconstructing the data from the subset of its features rather than its corrupted version in an autoencoder setting can better capture its underlying representation.
arXiv Detail & Related papers (2021-10-08T20:11:09Z) - SCARF: Self-Supervised Contrastive Learning using Random Feature
Corruption [72.35532598131176]
We propose SCARF, a technique for contrastive learning, where views are formed by corrupting a random subset of features.
We show that SCARF complements existing strategies and outperforms alternatives like autoencoders.
arXiv Detail & Related papers (2021-06-29T08:08:33Z) - Joining datasets via data augmentation in the label space for neural
networks [6.036150783745836]
We propose a new technique leveraging artificially created knowledge graph, recurrent neural networks and policy gradient that successfully achieve the dataset joining in the label space.
Empirical results on both image and text classification justify the validity of our approach.
arXiv Detail & Related papers (2021-06-17T06:08:11Z) - SLADE: A Self-Training Framework For Distance Metric Learning [75.54078592084217]
We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional unlabeled data.
We first train a teacher model on the labeled data and use it to generate pseudo labels for the unlabeled data.
We then train a student model on both labels and pseudo labels to generate final feature embeddings.
arXiv Detail & Related papers (2020-11-20T08:26:10Z) - Semantic Labeling Using a Deep Contextualized Language Model [9.719972529205101]
We propose a context-aware semantic labeling method using both the column values and context.
Our new method is based on a new setting for semantic labeling, where we sequentially predict labels for an input table with missing headers.
To our knowledge, we are the first to successfully apply BERT to solve the semantic labeling task.
arXiv Detail & Related papers (2020-10-30T03:04:22Z) - i-Mix: A Domain-Agnostic Strategy for Contrastive Representation
Learning [117.63815437385321]
We propose i-Mix, a simple yet effective domain-agnostic regularization strategy for improving contrastive representation learning.
In experiments, we demonstrate that i-Mix consistently improves the quality of learned representations across domains.
arXiv Detail & Related papers (2020-10-17T23:32:26Z) - Structured Prediction with Partial Labelling through the Infimum Loss [85.4940853372503]
The goal of weak supervision is to enable models to learn using only forms of labelling which are cheaper to collect.
This is a type of incomplete annotation where, for each datapoint, supervision is cast as a set of labels containing the real one.
This paper provides a unified framework based on structured prediction and on the concept of infimum loss to deal with partial labelling.
arXiv Detail & Related papers (2020-03-02T13:59:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.