Contextual Explanation Networks

By Maruan Al-Shedivat, Kumar Avinava Dubey, Eric P. Xing. 2017

90 citations recorded by the source corpus.

Modern learning algorithms excel at producing accurate but complex models of the data. However, deploying such models in the real-world requires extra care: we must ensure their reliability, robustness, and absence of undesired biases. This motivates the development of models that are equally accurate but can be also easily inspected and assessed beyond their predictive performance. To this end, we introduce contextual explanation networks (CEN)---a class of architectures that learn to predict by generating and utilizing intermediate, simplified probabilistic models. Specifically, CENs generate parameters for intermediate graphical models which are further used for prediction and play the role of explanations. Contrary to the existing post-hoc model-explanation tools, CENs learn to predict and to explain simultaneously. Our approach offers two major advantages: (i) for each prediction valid, instance-specific explanation is generated with no computational overhead and (ii) prediction via explanation acts as a regularizer and boosts performance in data-scarce settings. We analyze the proposed framework theoretically and experimentally. Our results on image and text classification and survival analysis tasks demonstrate that CENs are not only competitive with the state-of-the-art methods but also offer additional insights behind each prediction, that can be valuable for decision support. We also show that while post-hoc methods may produce misleading explanations in certain cases, CENs are consistent and allow to detect such cases systematically.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Interpretability Beyond Classification Output: Semantic Bottleneck Networks (2019, background): “erent interpretability has just recently gained more attention with more work focusing on making the predictions based on human interpretable concepts or prototypes. Similar to our proposed approach, [1, 20] and [16] embed an interpretable layer into the network, yet are different in the way that th”
Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments (2017, background): “…in the past [32–34], and more recent approaches that focused on learning optimizers for deep networks [13, 35–37], generating model parameters [38– 40], learning task embeddings [14, 41] including memory-based approaches [12], learning to learn implicitly via RL [42, 43], or simply learning a…”
Towards Robust Interpretability with Self-Explaining Neural Networks (2018, background): “Contextual Explanation Networks [19] are also inspired by the goal of designing a class of models that learns to predict and explain jointly, but differ from our approach in their formulation (through deep graphical models) and realization of the model (through variational autoencoders).”
Modular meta-learning (2018, methodology): “Johnson et al. [13] later showed that the structure controller could be trained with RL; others applied similar frameworks to get more interpretability [14] or to generalize across hierarchical robotic tasks with neural programs[15].”
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks (2017, background): “[1] proposed contextual explanation networks (CENs), a class of models that jointly learns to predict and explain its decision.”
Contextual Parameter Generation for Universal Neural Machine Translation (2018, methodology): “Al-Shedivat et al. (2017) also propose a related method where a neural network generates the parameters of a linear model.”
Generative causal explanations of black-box classifiers (2020, methodology): “This type of latent factor explanation has also been used in the construction of self-explaining neural networks [37, 40].”
Regularizing Black-box Models for Improved Interpretability (2019, background): “First, self-explaining neural networks (SENN) (Alvarez-Melis and Jaakkola, 2018a) (a variation of contextual explanation networks (CEN) (Al-Shedivat et al., 2017)) is an interpretable by-design approach that additionally (indirectly) optimizes their models to produce stable explanations.”
Interpretable Machine Learning in Healthcare (2018, background): “In some machine learning models like decision trees [24], regression models [33], and context explanation networks [3] the explanation itself is part of the model.”
Explainable artificial intelligence: a comprehensive review (2021, background): “Other approaches have shown that the hybrid interpretable models simultaneously learn and provide explanations with both symbolic descriptions, sub-symbolic descriptions, and inferences (Al-Shedivat et al. 2020).”
Text Generation with Exemplar-based Adaptive Decoding (2019, unknown): “It is later revisited with representation learning (Moczulski et al., 2015; Fer-nando et al., 2016; Al-Shedivat et al., 2017, inter alia ), and successfully applied to classiﬁcation (Jia et al., 2016; Liu et al., 2017) and machine translation (Platanios et al., 2018).”
Explainable Sentiment Analysis with Applications in Medicine (2018, background): “For example, Local Interpretable Model-agnostic Explanations (LIME) [6], [7], Layer-Wise Relevance Propagation [8], DeepLift [9], Contextual Explanation Networks (CEN) [10].”