21 papers · ranked by Valyu relevance
Michael Mayer, Mario V. Wüthrich
Originally introduced in cooperative game theory, Shapley values have become a very popular tool to explain machine learning predictions. Based on Shapley's fairness axioms, every input (feature component) gets a credit how it contributes to an output (prediction). These credits are then used to explain the prediction.…
Mingming Chen, Qihang Qian, Xiang Pan, Tenglong Li
Introduction Machine learning models have been employed to predict COVID-19 infections and mortality, but many models were built on training and testing sets from different periods. The purpose of this study is to investigate the impact of temporality, i.e., the temporal gap between training and testing sets, on model…
Zhuofan Jia, Jian Zhong Pei
—The Shapley value provides a principled framework for fairly distributing rewards among participants according to their individual contributions. While prior work has applied this concept to data valuation in machine learning, existing formulations overwhelmingly assume that each participant contributes a fixed…
Liuqing Yang, Yongdao Zhou, Haoda Fu, Min‐Qian Liu + 1 more
Shapley value is originally a concept in econometrics to fairly distribute both gains and costs to players in a coalition game. In the recent decades, its application has been extended to other areas such as marketing, engineering and machine learning. For example, it produces reasonable solutions for problems in…
Tomohiro Ishibashi, Akio Onogi
Mapping quantitative trait loci (QTLs) is one of the major goals of quantitative genetics; however, identifying the interactions between QTLs remains challenging. Recently developed machine learning methods, such as deep learning and gradient boosting, are transforming the real world. These methods could advance QTL…
Iain Burge, Michel Barbeau, Joaquín García-Alfaro
—In the classical context, the cooperative game theory concept of the Shapley value has been adapted for post hoc explanations of Machine Learning (ML) models. However, this approach does not easily translate to eXplainable Quantum ML (XQML). Finding Shapley values can be highly computationally complex. We propose…
Iain Burge, Michel Barbeau, Joaquín García-Alfaro
This work focuses on developing efficient post-hoc explanations for quantum AI algorithms. In classical contexts, the cooperative game theory concept of the Shapley value adapts naturally to post-hoc explanations, where it can be used to identify which factors are important in an AI's decision-making process. An…
Kawin Ethayarajh, Dan Jurafsky
Shapley Values, a solution to the credit assignment problem in cooperative game theory, are a popular type of explanation in machine learning, having been used to explain the importance of features, embeddings, and even neurons. In NLP, however, leave-oneout and attention-based explanations still predominate. Can we…
Iqbal Madakkatel, Elina Hyppönen
Background Shapley values have been used extensively in machine learning, not only to explain black box machine learning models, but among other tasks, also to conduct model debugging, sensitivity and fairness analyses and to select important features for robust modelling and for further follow-up analyses. Shapley…
Tannista Banerjee, Ayan Paul, Vishak Srikanth, Inga Strümke
With the increasing use of machine learning models in computational socioeconomics, the development of methods for explaining these models and understanding the causal connections is gradually gaining importance. In this work, we advocate the use of an explanatory framework from cooperative game theory augmented with…
Andrea Mastropietro, Christian Feldmann, Jürgen Bajorath
Machine learning (ML) algorithms are extensively used in pharmaceutical research. Most ML models have black-box character, thus preventing the interpretation of predictions. However, rationalizing model decisions is of critical importance if predictions should aid in experimental design. Accordingly, in…
Xiaoqing Li, Xiaoling Ji, Hongbum Kim
This study evaluates the efficiency of China’s industry-university-research collaborative innovation (IURCI) system using a two-stage game cross-efficiency model integrated with Shapley values. By constructing an evaluation index system that captures the two stages of innovation: research and development (R&D) and…
Teemu Kuosmanen, Juhani Rantanen, Dovydas Kičiatovas, Sanna Pausio + 4 more
Understanding and predicting how communities assemble is a paramount challenge in ecology. Here we address these questions normatively by comparing the observed species abundance distribution to a game-theoretically fair distribution based on each species’ Shapley value. By analyzing in total 56 distinct community…
Siyi Tang, Amirata Ghorbani, Rikiya Yamashita, Sameer Rehman + 3 more
'Jared A. Dunnmon' 'James Zou' 'Daniel L. Rubin'] The reliability of machine learning models can be compromised when trained on low quality data. Many large-scale medical imaging datasets contain low quality labels extracted from sources such as medical reports. Moreover, images within a dataset may have heterogeneous…
Yongchan Kwon, Sokbae Lee, Guillaume Pouliot
We propose a variant of the Shapley value, the group Shapley value, to interpret counterfactual simulations in structural economic models by quantifying the importance of different components. Our framework compares two sets of parameters, partitioned into multiple groups, and applying group Shapley value decomposition…
Teemu Kuosmanen, Juhani Rantanen, Dovydas Kičiatovas, Sanna Pausio + 3 more
Understanding and predicting how communities assemble is a paramount challenge in ecology. Here we address these questions normatively by comparing the ecological distribution of growth surplus to a game-theoretically fair distribution based on each species’ Shapley value. By analyzing in total 56 distinct community…
Tomás M. Coronado, Gabriel Riera, Francesc Rosselló
The Fair Proportion of a species in a phylogenetic tree is a very simple measure that has been used to assess its value relative to the overall phylogenetic diversity represented by the tree. It has recently been proved by Fuchs and Jin to be equal to the Shapley Value of the coallitional game that sends each subset of…
Iain Martyn, Tyler S Kuhn, Arne O Mooers, Vincent Moulton + 1 more
'Andreas Spillner'] We present optimal linear time algorithms for computing the Shapley values and 'heightened evolutionary distinctiveness' (HED) scores for the set of taxa in a phylogenetic tree. We demonstrate the efficiency of these new algorithms by applying them to a set of 10,000 reasonable 5139-species mammal…
Boyang Zhao
There is increasing emphasis on the interpretability of machine learning models, including in understanding biological systems. The well-known Shapley value framework based on game theory works in principle with any models to attribute feature importance. While feature interactions are critical to understand and can be…
Authors not listed
Chalcogenide Hybrid Inorganic/Organic Polymers (CHIPs) have the potential to revolutionize infrared (IR) optics and create sustainable and recyclable devices. CHIPs combine elemental sulfur with organic comonomers via inverse vulcanization to create a high-sulfur content polymer, with optical properties that rival…
Joshua Hesse, Davide Boldini, Stephan Sieber
In the rapidly evolving field of drug discovery, High Throughput Screening (HTS) is a pivotal technique for identifying promising compounds. Despite its wide usage, the primary challenge remains in efficiently sifting through vast chemical libraries to discern true bioactive compounds from false positives. This study…