Efficient Classification with Counterfactual Reasoning and Active
Learning
- URL: http://arxiv.org/abs/2207.12086v1
- Date: Mon, 25 Jul 2022 12:03:40 GMT
- Title: Efficient Classification with Counterfactual Reasoning and Active
Learning
- Authors: Azhar Mohammed, Dang Nguyen, Bao Duong, Thin Nguyen
- Abstract summary: Methods called CCRAL combine causal reasoning to learn counterfactual samples for the original training samples and active learning to select useful counterfactual samples based on a region of uncertainty.
Experiments show that CCRAL achieves significantly better performance than those of the baselines in terms of accuracy and AUC.
- Score: 4.708737212700907
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Data augmentation is one of the most successful techniques to improve the
classification accuracy of machine learning models in computer vision. However,
applying data augmentation to tabular data is a challenging problem since it is
hard to generate synthetic samples with labels. In this paper, we propose an
efficient classifier with a novel data augmentation technique for tabular data.
Our method called CCRAL combines causal reasoning to learn counterfactual
samples for the original training samples and active learning to select useful
counterfactual samples based on a region of uncertainty. By doing this, our
method can maximize our model's generalization on the unseen testing data. We
validate our method analytically, and compare with the standard baselines. Our
experimental results highlight that CCRAL achieves significantly better
performance than those of the baselines across several real-world tabular
datasets in terms of accuracy and AUC. Data and source code are available at:
https://github.com/nphdang/CCRAL.
Related papers
- Stabilizing Subject Transfer in EEG Classification with Divergence
Estimation [17.924276728038304]
We propose several graphical models to describe an EEG classification task.
We identify statistical relationships that should hold true in an idealized training scenario.
We design regularization penalties to enforce these relationships in two stages.
arXiv Detail & Related papers (2023-10-12T23:06:52Z) - Improved Distribution Matching for Dataset Condensation [91.55972945798531]
We propose a novel dataset condensation method based on distribution matching.
Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
arXiv Detail & Related papers (2023-07-19T04:07:33Z) - Exploring Data Redundancy in Real-world Image Classification through
Data Selection [20.389636181891515]
Deep learning models often require large amounts of data for training, leading to increased costs.
We present two data valuation metrics based on Synaptic Intelligence and gradient norms, respectively, to study redundancy in real-world image data.
Online and offline data selection algorithms are then proposed via clustering and grouping based on the examined data values.
arXiv Detail & Related papers (2023-06-25T03:31:05Z) - Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data.
We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
arXiv Detail & Related papers (2023-03-06T14:49:59Z) - Active Learning with Combinatorial Coverage [0.0]
Active learning is a practical field of machine learning that automates the process of selecting which data to label.
Current methods are effective in reducing the burden of data labeling but are heavily model-reliant.
This has led to the inability of sampled data to be transferred to new models as well as issues with sampling bias.
We propose active learning methods utilizing coverage to overcome these issues.
arXiv Detail & Related papers (2023-02-28T13:43:23Z) - Too Fine or Too Coarse? The Goldilocks Composition of Data Complexity
for Robust Left-Right Eye-Tracking Classifiers [0.0]
We train machine learning models utilizing a mixed dataset composed of both fine- and coarse-grain data.
For our purposes, finer-grain data refers to data collected using more complex methods whereas coarser-grain data refers to data collected using more simple methods.
arXiv Detail & Related papers (2022-08-24T23:18:08Z) - Efficient training of lightweight neural networks using Online
Self-Acquired Knowledge Distillation [51.66271681532262]
Online Self-Acquired Knowledge Distillation (OSAKD) is proposed, aiming to improve the performance of any deep neural model in an online manner.
We utilize k-nn non-parametric density estimation technique for estimating the unknown probability distributions of the data samples in the output feature space.
arXiv Detail & Related papers (2021-08-26T14:01:04Z) - No Fear of Heterogeneity: Classifier Calibration for Federated Learning
with Non-IID Data [78.69828864672978]
A central challenge in training classification models in the real-world federated system is learning with non-IID data.
We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model.
Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
arXiv Detail & Related papers (2021-06-09T12:02:29Z) - ALT-MAS: A Data-Efficient Framework for Active Testing of Machine
Learning Algorithms [58.684954492439424]
We propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data.
The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN)
arXiv Detail & Related papers (2021-04-11T12:14:04Z) - On the Robustness of Active Learning [0.7340017786387767]
Active Learning is concerned with how to identify the most useful samples for a Machine Learning algorithm to be trained with.
We find that it is often applied with not enough care and domain knowledge.
We propose the new "Sum of Squared Logits" method based on the Simpson diversity index and investigate the effect of using the confusion matrix for balancing in sample selection.
arXiv Detail & Related papers (2020-06-18T09:07:23Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z)
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.