ProtoTEx: Explaining Model Decisions with Prototype Tensors
- URL: http://arxiv.org/abs/2204.05426v2
- Date: Mon, 23 May 2022 00:34:37 GMT
- Title: ProtoTEx: Explaining Model Decisions with Prototype Tensors
- Authors: Anubrata Das and Chitrank Gupta and Venelin Kovatchev and Matthew
Lease and Junyi Jessy Li
- Abstract summary: ProtoTEx is a novel white-box NLP classification architecture based on prototype networks.
We describe a novel interleaved training algorithm that effectively handles classes characterized by the absence of indicative features.
On a propaganda detection task, ProtoTEx accuracy matches BART-large and exceeds BERT-large with the added benefit of providing faithful explanations.
- Score: 27.779971257213553
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We present ProtoTEx, a novel white-box NLP classification architecture based
on prototype networks. ProtoTEx faithfully explains model decisions based on
prototype tensors that encode latent clusters of training examples. At
inference time, classification decisions are based on the distances between the
input text and the prototype tensors, explained via the training examples most
similar to the most influential prototypes. We also describe a novel
interleaved training algorithm that effectively handles classes characterized
by the absence of indicative features. On a propaganda detection task, ProtoTEx
accuracy matches BART-large and exceeds BERT-large with the added benefit of
providing faithful explanations. A user study also shows that prototype-based
explanations help non-experts to better recognize propaganda in online news.
Related papers
- Mixed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation [0.0]
We propose the Mixed Prototype Consistency Learning (MPCL) framework, which includes a Mean Teacher and an auxiliary network.
The Mean Teacher generates prototypes for labeled and unlabeled data, while the auxiliary network produces additional prototypes for mixed data processed by CutMix.
High-quality global prototypes for each class are formed by fusing two enhanced prototypes, optimizing the distribution of hidden embeddings used in consistency learning.
arXiv Detail & Related papers (2024-04-16T16:51:12Z) - MProto: Multi-Prototype Network with Denoised Optimal Transport for
Distantly Supervised Named Entity Recognition [75.87566793111066]
We propose a noise-robust prototype network named MProto for the DS-NER task.
MProto represents each entity type with multiple prototypes to characterize the intra-class variance.
To mitigate the noise from incomplete labeling, we propose a novel denoised optimal transport (DOT) algorithm.
arXiv Detail & Related papers (2023-10-12T13:02:34Z) - Transductive Few-shot Learning with Prototype-based Label Propagation by
Iterative Graph Refinement [41.726774734996766]
We propose a novel prototype-based label propagation method for few-shot learning.
Specifically, our graph construction is based on the relation between prototypes and samples rather than between samples.
On mini-ImageNet, tiered-ImageNet, CIFAR-FS and CUB datasets, we show the proposed method outperforms other state-of-the-art methods.
arXiv Detail & Related papers (2023-04-23T10:09:26Z) - Learning Support and Trivial Prototypes for Interpretable Image
Classification [19.00622056840535]
Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable classification.
We aim to improve the classification of ProtoPNet with a new method to learn support prototypes that lie near the classification boundary in the feature space.
arXiv Detail & Related papers (2023-01-08T09:27:41Z) - Rethinking Semantic Segmentation: A Prototype View [126.59244185849838]
We present a nonparametric semantic segmentation model based on non-learnable prototypes.
Our framework yields compelling results over several datasets.
We expect this work will provoke a rethink of the current de facto semantic segmentation model design.
arXiv Detail & Related papers (2022-03-28T21:15:32Z) - Dual Prototypical Contrastive Learning for Few-shot Semantic
Segmentation [55.339405417090084]
We propose a dual prototypical contrastive learning approach tailored to the few-shot semantic segmentation (FSS) task.
The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space.
We demonstrate that the proposed dual contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets.
arXiv Detail & Related papers (2021-11-09T08:14:50Z) - Prototype Completion for Few-Shot Learning [13.63424509914303]
Few-shot learning aims to recognize novel classes with few examples.
Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning.
We propose a novel prototype completion based meta-learning framework.
arXiv Detail & Related papers (2021-08-11T03:44:00Z) - Prototypical Representation Learning for Relation Extraction [56.501332067073065]
This paper aims to learn predictive, interpretable, and robust relation representations from distantly-labeled data.
We learn prototypes for each relation from contextual information to best explore the intrinsic semantics of relations.
Results on several relation learning tasks show that our model significantly outperforms the previous state-of-the-art relational models.
arXiv Detail & Related papers (2021-03-22T08:11:43Z) - Toward Scalable and Unified Example-based Explanation and Outlier
Detection [128.23117182137418]
We argue for a broader adoption of prototype-based student networks capable of providing an example-based explanation for their prediction.
We show that our prototype-based networks beyond similarity kernels deliver meaningful explanations and promising outlier detection results without compromising classification accuracy.
arXiv Detail & Related papers (2020-11-11T05:58:17Z) - Prototype Completion with Primitive Knowledge for Few-Shot Learning [20.449056536438658]
Few-shot learning is a challenging task, which aims to learn a classifier for novel classes with few examples.
Pre-training based meta-learning methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning.
We propose a novel prototype completion based meta-learning framework.
arXiv Detail & Related papers (2020-09-10T16:09:34Z) - Prototypical Contrastive Learning of Unsupervised Representations [171.3046900127166]
Prototypical Contrastive Learning (PCL) is an unsupervised representation learning method.
PCL implicitly encodes semantic structures of the data into the learned embedding space.
PCL outperforms state-of-the-art instance-wise contrastive learning methods on multiple benchmarks.
arXiv Detail & Related papers (2020-05-11T09:53:36Z)
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.