GLANCE: Global to Local Architecture-Neutral Concept-based Explanations
- URL: http://arxiv.org/abs/2207.01917v1
- Date: Tue, 5 Jul 2022 09:52:09 GMT
- Title: GLANCE: Global to Local Architecture-Neutral Concept-based Explanations
- Authors: Avinash Kori, Ben Glocker, Francesca Toni
- Abstract summary: We propose a novel twin-surrogate explainability framework to explain the decisions made by any CNN-based image classifier.
We first disentangle latent features from the classifier, followed by aligning these features to observed/human-defined context' features.
These aligned features form semantically meaningful concepts that are used for extracting a causal graph depicting the perceived' data-generating process.
We provide a generator to visualize the effect' of interactions among features in latent space and draw feature importance therefrom as local explanations.
- Score: 26.76139301708958
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Most of the current explainability techniques focus on capturing the
importance of features in input space. However, given the complexity of models
and data-generating processes, the resulting explanations are far from being
`complete', in that they lack an indication of feature interactions and
visualization of their `effect'. In this work, we propose a novel
twin-surrogate explainability framework to explain the decisions made by any
CNN-based image classifier (irrespective of the architecture). For this, we
first disentangle latent features from the classifier, followed by aligning
these features to observed/human-defined `context' features. These aligned
features form semantically meaningful concepts that are used for extracting a
causal graph depicting the `perceived' data-generating process, describing the
inter- and intra-feature interactions between unobserved latent features and
observed `context' features. This causal graph serves as a global model from
which local explanations of different forms can be extracted. Specifically, we
provide a generator to visualize the `effect' of interactions among features in
latent space and draw feature importance therefrom as local explanations. Our
framework utilizes adversarial knowledge distillation to faithfully learn a
representation from the classifiers' latent space and use it for extracting
visual explanations. We use the styleGAN-v2 architecture with an additional
regularization term to enforce disentanglement and alignment. We demonstrate
and evaluate explanations obtained with our framework on Morpho-MNIST and on
the FFHQ human faces dataset. Our framework is available at
\url{https://github.com/koriavinash1/GLANCE-Explanations}.
Related papers
- Situational Scene Graph for Structured Human-centric Situation Understanding [15.91717913059569]
We propose a graph-based representation called Situational Scene Graph (SSG) to encode both humanobject-relationships and the corresponding semantic properties.
The semantic details are represented as predefined roles and values inspired by situation frame, which is originally designed to represent a single action.
We will release the code and the dataset soon.
arXiv Detail & Related papers (2024-10-30T09:11:25Z) - Feature Accentuation: Revealing 'What' Features Respond to in Natural Images [4.4273123155989715]
We introduce a new method to the interpretability tool-kit, 'feature accentuation', which is capable of conveying both where and what in arbitrary input images induces a feature's response.
We find a particular combination of parameterization, augmentation, and regularization yields naturalistic visualizations that resemble the seed image and target feature simultaneously.
We make our precise implementation of feature accentuation available to the community as the Faccent library, an extension of Lucent.
arXiv Detail & Related papers (2024-02-15T16:01:59Z) - KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot
Node Classification [75.95647590619929]
Zero-Shot Node Classification (ZNC) has been an emerging and crucial task in graph data analysis.
We propose a Knowledge-Aware Multi-Faceted framework (KMF) that enhances the richness of label semantics.
A novel geometric constraint is developed to alleviate the problem of prototype drift caused by node information aggregation.
arXiv Detail & Related papers (2023-08-15T02:38:08Z) - Identifying Interpretable Subspaces in Image Representations [54.821222487956355]
We propose a framework to explain features of image representations using Contrasting Concepts (FALCON)
For a target feature, FALCON captions its highly activating cropped images using a large captioning dataset and a pre-trained vision-language model like CLIP.
Each word among the captions is scored and ranked leading to a small number of shared, human-understandable concepts.
arXiv Detail & Related papers (2023-07-20T00:02:24Z) - Conversational Semantic Parsing using Dynamic Context Graphs [68.72121830563906]
We consider the task of conversational semantic parsing over general purpose knowledge graphs (KGs) with millions of entities, and thousands of relation-types.
We focus on models which are capable of interactively mapping user utterances into executable logical forms.
arXiv Detail & Related papers (2023-05-04T16:04:41Z) - Cross-modal Representation Learning for Zero-shot Action Recognition [67.57406812235767]
We present a cross-modal Transformer-based framework, which jointly encodes video data and text labels for zero-shot action recognition (ZSAR)
Our model employs a conceptually new pipeline by which visual representations are learned in conjunction with visual-semantic associations in an end-to-end manner.
Experiment results show our model considerably improves upon the state of the arts in ZSAR, reaching encouraging top-1 accuracy on UCF101, HMDB51, and ActivityNet benchmark datasets.
arXiv Detail & Related papers (2022-05-03T17:39:27Z) - BSAL: A Framework of Bi-component Structure and Attribute Learning for
Link Prediction [33.488229191263564]
We propose a bicomponent structural and attribute learning framework (BSAL) that is designed to adaptively leverage information from topology and feature spaces.
BSAL constructs a semantic topology via the node attributes and then gets the embeddings regarding the semantic view.
It provides a flexible and easy-to-implement solution to adaptively incorporate the information carried by the node attributes.
arXiv Detail & Related papers (2022-04-18T03:12:13Z) - GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the
Language of Motifs [11.453325862543094]
GRAPHSHAP is able to provide motif-based explanations for identity-aware graph classifiers.
We show how a simple kernel can efficiently approximate explanation scores, thus allowing GRAPHSHAP to scale on scenarios with a large explanation space.
Our experiments highlight how the classification provided by a black-box model can be effectively explained by few connectomics patterns.
arXiv Detail & Related papers (2022-02-17T18:29:30Z) - Semantic Disentangling Generalized Zero-Shot Learning [50.259058462272435]
Generalized Zero-Shot Learning (GZSL) aims to recognize images from both seen and unseen categories.
In this paper, we propose a novel feature disentangling approach based on an encoder-decoder architecture.
The proposed model aims to distill quality semantic-consistent representations that capture intrinsic features of seen images.
arXiv Detail & Related papers (2021-01-20T05:46:21Z) - Towards Efficient Scene Understanding via Squeeze Reasoning [71.1139549949694]
We propose a novel framework called Squeeze Reasoning.
Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector.
We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks.
arXiv Detail & Related papers (2020-11-06T12:17:01Z) - Improving Coreference Resolution by Leveraging Entity-Centric Features
with Graph Neural Networks and Second-order Inference [12.115691569576345]
Coreferent mentions usually spread far apart in an entire text, making it difficult to incorporate entity-level features.
We propose a graph neural network-based coreference resolution method that can capture the entity-centric information.
A global inference algorithm up to second-order features is also presented to optimally cluster mentions into consistent groups.
arXiv Detail & Related papers (2020-09-10T02:22:21Z)
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.