Collaborating Authors

shapley value

Guide to Interpretable Machine Learning


If you can't explain it simply, you don't understand it well enough. Disclaimer: This article draws and expands upon material from (1) Christoph Molnar's excellent book on Interpretable Machine Learning which I definitely recommend to the curious reader, (2) a deep learning visualization workshop from Harvard ComputeFest 2020, as well as (3) material from CS282R at Harvard University taught by Ike Lage and Hima Lakkaraju, who are both prominent researchers in the field of interpretability and explainability. This article is meant to condense and summarize the field of interpretable machine learning to the average data scientist and to stimulate interest in the subject. Machine learning systems are becoming increasingly employed in complex high-stakes settings such as medicine (e.g. Despite this increased utilization, there is still a lack of sufficient techniques available to be able to explain and interpret the decisions of these deep learning algorithms. This can be very problematic in some areas where the decisions of algorithms must be explainable or attributable to certain features due to laws or regulations (such as the right to explanation), or where accountability is required. The need for algorithmic accountability has been highlighted many times, the most notable cases of which are Google's facial recognition algorithm that labeled some black people as gorillas, and Uber's self-driving car which ran a stop sign. Due to the inability of Google to fix the algorithm and remove the algorithmic bias that resulted in this issue, they solved the problem by removing words relating to monkeys from Google Photo's search engine. This illustrates the alleged black box nature of many machine learning algorithms. The black box problem is predominantly associated with the supervised machine learning paradigm due to its predictive nature. Accuracy alone is no longer enough. Academics in deep learning are acutely aware of this interpretability and explainability problem, and whilst some argue that these models are essentially black boxes, there have been several developments in recent years which have been developed for visualizing aspects of deep neural networks such the features and representations they have learned. The term info-besity has been thrown around to refer to the difficulty of providing transparency when decisions are made on the basis of many individual features, due to an overload of information.

On Anomaly Interpretation via Shapley Values Machine Learning

Anomaly localization is an essential problem as anomaly detection is. Because a rigorous localization requires a causal model of a target system, practically we often resort to a relaxed problem of anomaly interpretation, for which we are to obtain meaningful attribution of anomaly scores to input features. In this paper, we investigate the use of the Shapley value for anomaly interpretation. We focus on the semi-supervised anomaly detection and newly propose a characteristic function, on which the Shapley value is computed, specifically for anomaly scores. The idea of the proposed method is approximating the absence of some features by minimizing an anomaly score with regard to them. We examine the performance of the proposed method as well as other general approaches to computing the Shapley value in interpreting anomaly scores. We show the results of experiments on multiple datasets and anomaly detection methods, which indicate the usefulness of the Shapley-based anomaly interpretation toward anomaly localization.

Understanding Global Feature Contributions Through Additive Importance Measures Machine Learning

Understanding the inner workings of complex machine learning models is a long-standing problem, with recent research focusing primarily on local interpretability. To assess the role of individual input features in a global sense, we propose a new feature importance method, Shapley Additive Global importancE (SAGE), a model-agnostic measure of feature importance based on the predictive power associated with each feature. SAGE relates to prior work through the novel framework of additive importance measures, a perspective that unifies numerous other feature importance methods and shows that only SAGE properly accounts for complex feature interactions. We define SAGE using the Shapley value from cooperative game theory, which leads to numerous intuitive and desirable properties. Our experiments apply SAGE to eight datasets, including MNIST and breast cancer subtype classification, and demonstrate its advantages through quantitative and qualitative evaluations.

6 Python Libraries to Interpret Machine Learning Models and Build Trust - Analytics Vidhya


The'SHapley Additive exPlanations' Python library, better knows as the SHAP library, is one of the most popular libraries for machine learning interpretability. The SHAP library uses Shapley values at its core and is aimed at explaining individual predictions. But wait – what are Shapley values? Simply put, Shapley values are derived from Game Theory, where each feature in our data is a player, and the final reward is the prediction. Depending on the reward, Shapley values tell us how to distribute this reward among the players fairly. We won't cover this technique in detail here, but you can refer to this excellent article explaining how Shapley values work: A Unique Method for Machine Learning Interpretability: Game Theory & Shapley Values! The best part about SHAP is that it offers a special module for tree-based models. Considering how popular tree-based models are in hackathons and in the industry, this module makes fast computations, even considering dependent features.

Overview of Neural Architecture Search Paperspace Blog


The hyperparameter optimization problem has been solved in many different ways for classical machine learning algorithms. Some examples include the use of grid search, random search, Bayesian optimization, meta-learning, and so on. But when considering deep learning architectures, the problem becomes much harder to deal with. In this article we will cover the problem of neural architecture search and the current state of the art. This article assumes a basic knowledge of different neural networks and deep learning architectures. This is Part 1 of a series which will take you through what the problem of neural architecture search (NAS) is, and how to implement various interesting approaches for NAS using Keras. Deep learning engineers are expected to have an intuitive understanding of what architecture might work best for what situation, but this is rarely the case. The possible architectures one can create are endless.

Absolute Shapley Value Machine Learning

Shapley value is a concept in cooperative game theory for measuring the contribution of each participant, which was named in honor of Lloyd Shapley. Shapley value has been recently applied in data marketplaces for compensation allocation based on their contribution to the models. Shapley value is the only value division scheme used for compensation allocation that meets three desirable criteria: group rationality, fairness, and additivity. In cooperative game theory, the marginal contribution of each contributor to each coalition is a nonnegative value. However, in machine learning model training, the marginal contribution of each contributor (data tuple) to each coalition (a set of data tuples) can be a negative value, i.e., the accuracy of the model trained by a dataset with an additional data tuple can be lower than the accuracy of the model trained by the dataset only. In this paper, we investigate the problem of how to handle the negative marginal contribution when computing Shapley value. We explore three philosophies: 1) taking the original value (Original Shapley Value); 2) taking the larger of the original value and zero (Zero Shapley Value); and 3) taking the absolute value of the original value (Absolute Shapley Value). Experiments on Iris dataset demonstrate that the definition of Absolute Shapley Value significantly outperforms the other two definitions in terms of evaluating data importance (the contribution of each data tuple to the trained model).

A Distributional Framework for Data Valuation Machine Learning

Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its foundational role, a key limitation of the data Shapley framework is that it only provides valuations for points within a fixed data set. It does not account for statistical aspects of the data and does not give a way to reason about points outside the data set. To address these limitations, we propose a novel framework -- distributional Shapley -- where the value of a point is defined in the context of an underlying data distribution. We prove that distributional Shapley has several desirable statistical properties; for example, the values are stable under perturbations to the data points themselves and to the underlying data distribution. We leverage these properties to develop a new algorithm for estimating values from data, which comes with formal guarantees and runs two orders of magnitude faster than state-of-the-art algorithms for computing the (non-distributional) data Shapley values. We apply distributional Shapley to diverse data sets and demonstrate its utility in a data market setting.

Neuron Shapley: Discovering the Responsible Neurons Machine Learning

We develop Neuron Shapley as a new framework to quantify the contribution of individual neurons to the prediction and performance of a deep network. By accounting for interactions across neurons, Neuron Shapley is more effective in identifying important filters compared to common approaches based on activation patterns. Interestingly, removing just 30 filters with the highest Shapley scores effectively destroys the prediction accuracy of Inception-v3 on ImageNet. Visualization of these few critical filters provides insights into how the network functions. Neuron Shapley is a flexible framework and can be applied to identify responsible neurons in many tasks. We illustrate additional applications of identifying filters that are responsible for biased prediction in facial recognition and filters that are vulnerable to adversarial attacks. Removing these filters is a quick way to repair models. Enabling all these applications is a new multi-arm bandit algorithm that we developed to efficiently estimate Neuron Shapley values.

FedCoin: A Peer-to-Peer Payment System for Federated Learning Machine Learning

Federated learning (FL) is an emerging collaborative machine learning method to train models on distributed datasets with privacy concerns. To properly incentivize data owners to contribute their efforts, Shapley Value (SV) is often adopted to fairly assess their contribution. However, the calculation of SV is time-consuming and computationally costly. In this paper, we propose FedCoin, a blockchain-based peer-to-peer payment system for FL to enable a feasible SV based profit distribution. In FedCoin, blockchain consensus entities calculate SVs and a new block is created based on the proof of Shapley (PoSap) protocol. It is in contrast to the popular BitCoin network where consensus entities "mine" new blocks by solving meaningless puzzles. Based on the computed SVs, a scheme for dividing the incentive payoffs among FL clients with nonrepudiation and tamper-resistance properties is proposed. Experimental results based on real-world data show that FedCoin can promote high-quality data from FL clients through accurately computing SVs with an upper bound on the computational resources required for reaching consensus. It opens opportunities for non-data owners to play a role in FL.