Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold

• URL: http://arxiv.org/abs/2404.12341v2
• Date: Mon, 07 Oct 2024 21:43:23 GMT
• Title: Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold
• Authors: Yinzhu Jin, Matthew B. Dwyer, P. Thomas Fletcher,
• Abstract summary: We introduce a new technique to measure the feature dependency of neural network models. The motivation is to better understand a model by querying whether it is using information from human-understandable features. We test our method on deep neural network models trained on synthetic image data with known ground truth.
• Score: 18.64569268049846
• License:
• Abstract: This paper introduces a new technique to measure the feature dependency of neural network models. The motivation is to better understand a model by querying whether it is using information from human-understandable features, e.g., anatomical shape, volume, or image texture. Our method is based on the principle that if a model is dependent on a feature, then removal of that feature should significantly harm its performance. A targeted feature is "removed" by collapsing the dimension in the data distribution that corresponds to that feature. We perform this by moving data points along the feature dimension to a baseline feature value while staying on the data manifold, as estimated by a deep generative model. Then we observe how the model's performance changes on the modified test data set, with the target feature dimension removed. We test our method on deep neural network models trained on synthetic image data with known ground truth, an Alzheimer's disease prediction task using MRI and hippocampus segmentations from the OASIS-3 dataset, and a cell nuclei classification task using the Lizard dataset.

Related papers

• The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease detection [51.697248252191265]
  This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation. We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare. Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
  arXiv  Detail & Related papers  (2023-09-13T10:40:41Z)
• Feature Gradient Flow for Interpreting Deep Neural Networks in Head and Neck Cancer Prediction [2.9477900773805032]
  This paper introduces feature gradient flow, a new technique for interpreting deep learning models in terms of features that are understandable to humans. We measure the agreement of interpretable features with the gradient flow of a model. We develop a technique for training neural networks to be more interpretable by adding a regularization term to the loss function.
  arXiv  Detail & Related papers  (2023-07-24T18:25:59Z)
• ProtoVAE: Prototypical Networks for Unsupervised Disentanglement [1.6114012813668934]
  We introduce a novel deep generative VAE-based model, ProtoVAE, that leverages a deep metric learning Prototypical network trained using self-supervision. Our model is completely unsupervised and requires no priori knowledge of the dataset, including the number of factors. We evaluate our proposed model on the benchmark dSprites, 3DShapes, and MPI3D disentanglement datasets.
  arXiv  Detail & Related papers  (2023-05-16T01:29:26Z)
• Human Semantic Segmentation using Millimeter-Wave Radar Sparse Point Clouds [3.3888257250564364]
  This paper presents a framework for semantic segmentation on sparse sequential point clouds of millimeter-wave radar. The sparsity and capturing temporal-topological features of mmWave data is still a problem. We introduce graph structure and topological features to the point cloud and propose a semantic segmentation framework. Our model achieves mean accuracy on a custom dataset by $mathbf82.31%$ and outperforms state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2023-04-27T12:28:06Z)
• Functional Neural Networks: Shift invariant models for functional data with applications to EEG classification [0.0]
  We introduce a new class of neural networks that are shift invariant and preserve smoothness of the data: functional neural networks (FNNs) For this, we use methods from functional data analysis (FDA) to extend multi-layer perceptrons and convolutional neural networks to functional data. We show that the models outperform a benchmark model from FDA in terms of accuracy and successfully use FNNs to classify electroencephalography (EEG) data.
  arXiv  Detail & Related papers  (2023-01-14T09:41:21Z)
• Neural Eigenfunctions Are Structured Representation Learners [93.53445940137618]
  This paper introduces a structured, adaptive-length deep representation called Neural Eigenmap. We show that, when the eigenfunction is derived from positive relations in a data augmentation setup, applying NeuralEF results in an objective function. We demonstrate using such representations as adaptive-length codes in image retrieval systems.
  arXiv  Detail & Related papers  (2022-10-23T07:17:55Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classification [4.992154875028543]
  Integration and analysis of multi-omics data give us a broad view of tumours, which can improve clinical decision making. SubOmiEmbed produces comparable results to the baseline OmiEmbed with a much smaller network and by using just a subset of the data. This work can be improved to integrate mutation-based genomic data as well.
  arXiv  Detail & Related papers  (2022-02-03T16:39:09Z)
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach [80.8446673089281]
  We propose a new learning paradigm with graph representation and learning. Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
  arXiv  Detail & Related papers  (2021-10-09T09:02:45Z)
• AttriMeter: An Attribute-guided Metric Interpreter for Person Re-Identification [100.3112429685558]
  Person ReID systems only provide a distance or similarity when matching two persons. We propose an Attribute-guided Metric Interpreter, named AttriMeter, to semantically and quantitatively explain the results of CNN-based ReID models.
  arXiv  Detail & Related papers  (2021-03-02T03:37:48Z)
• Data from Model: Extracting Data from Non-robust and Robust Models [83.60161052867534]
  This work explores the reverse process of generating data from a model, attempting to reveal the relationship between the data and the model. We repeat the process of Data to Model (DtM) and Data from Model (DfM) in sequence and explore the loss of feature mapping information. Our results show that the accuracy drop is limited even after multiple sequences of DtM and DfM, especially for robust models.
  arXiv  Detail & Related papers  (2020-07-13T05:27:48Z)

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.