Prototype Based Classification from Hierarchy to Fairness
- URL: http://arxiv.org/abs/2205.13997v1
- Date: Fri, 27 May 2022 14:21:41 GMT
- Title: Prototype Based Classification from Hierarchy to Fairness
- Authors: Mycal Tucker, Julie Shah
- Abstract summary: A new neural network architecture, the concept subspace network (CSN), generalizes existing specialized classifiers to produce a unified model.
CSNs reproduce state-of-the-art results in fair classification when enforcing concept independence.
The CSN is inspired by existing prototype-based classifiers that promote interpretability.
- Score: 7.129830575525267
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Artificial neural nets can represent and classify many types of data but are
often tailored to particular applications -- e.g., for "fair" or "hierarchical"
classification. Once an architecture has been selected, it is often difficult
for humans to adjust models for a new task; for example, a hierarchical
classifier cannot be easily transformed into a fair classifier that shields a
protected field. Our contribution in this work is a new neural network
architecture, the concept subspace network (CSN), which generalizes existing
specialized classifiers to produce a unified model capable of learning a
spectrum of multi-concept relationships. We demonstrate that CSNs reproduce
state-of-the-art results in fair classification when enforcing concept
independence, may be transformed into hierarchical classifiers, or even
reconcile fairness and hierarchy within a single classifier. The CSN is
inspired by existing prototype-based classifiers that promote interpretability.
Related papers
- Neuro-symbolic Rule Learning in Real-world Classification Tasks [75.0907310059298]
We extend pix2rule's neural DNF module to support rule learning in real-world multi-class and multi-label classification tasks.
We propose a novel extended model called neural DNF-EO (Exactly One) which enforces mutual exclusivity in multi-class classification.
arXiv Detail & Related papers (2023-03-29T13:27:14Z) - Learning Primitive-aware Discriminative Representations for Few-shot
Learning [28.17404445820028]
Few-shot learning aims to learn a classifier that can be easily adapted to recognize novel classes with only a few labeled examples.
We propose a Primitive Mining and Reasoning Network (PMRN) to learn primitive-aware representations.
Our method achieves state-of-the-art results on six standard benchmarks.
arXiv Detail & Related papers (2022-08-20T16:22:22Z) - Class-Specific Semantic Reconstruction for Open Set Recognition [101.24781422480406]
Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes.
We propose a novel method, called Class-Specific Semantic Reconstruction (CSSR), that integrates the power of auto-encoder (AE) and prototype learning.
Results of experiments conducted on multiple datasets show that the proposed method achieves outstanding performance in both close and open set recognition.
arXiv Detail & Related papers (2022-07-05T16:25:34Z) - Computing Class Hierarchies from Classifiers [12.631679928202516]
We propose a novel algorithm for automatically acquiring a class hierarchy from a neural network.
Our algorithm produces surprisingly good hierarchies for some well-known deep neural network models.
arXiv Detail & Related papers (2021-12-02T13:01:04Z) - Dynamic Inference with Neural Interpreters [72.90231306252007]
We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules.
inputs to the model are routed through a sequence of functions in a way that is end-to-end learned.
We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
arXiv Detail & Related papers (2021-10-12T23:22:45Z) - CondNet: Conditional Classifier for Scene Segmentation [46.62529212678346]
We present a conditional classifier to replace the traditional global classifier.
It attends on the intra-class distinction, leading to stronger dense recognition capability.
The framework equipped with the conditional classifier (called CondNet) achieves new state-of-the-art performances on two datasets.
arXiv Detail & Related papers (2021-09-21T17:19:09Z) - Polynomial Networks in Deep Classifiers [55.90321402256631]
We cast the study of deep neural networks under a unifying framework.
Our framework provides insights on the inductive biases of each model.
The efficacy of the proposed models is evaluated on standard image and audio classification benchmarks.
arXiv Detail & Related papers (2021-04-16T06:41:20Z) - Learning and Evaluating Representations for Deep One-class
Classification [59.095144932794646]
We present a two-stage framework for deep one-class classification.
We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations.
In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
arXiv Detail & Related papers (2020-11-04T23:33:41Z) - Learn Class Hierarchy using Convolutional Neural Networks [0.9569316316728905]
We propose a new architecture for hierarchical classification of images, introducing a stack of deep linear layers with cross-entropy loss functions and center loss combined.
We experimentally show that our hierarchical classifier presents advantages to the traditional classification approaches finding application in computer vision tasks.
arXiv Detail & Related papers (2020-05-18T12:06:43Z)
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.