If You Like Shapley Then You’ll Love the Core

Yan, Tom; Procaccia, Ariel D.

doi:10.1609/aaai.v35i6.16721

Cited by 21 publications

(3 citation statements)

References 19 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This thus indicates that all the existing data Shapley dependent solutions are computationally intractable for our problem. Although there have been many recent attempts to approximately but efficiently compute data Shapley values, e.g., [Jia et al 2019, Yan andProcaccia 2021, Jia et al], they are still far from being practical solutions since they either explicitly assume that the models have certain properties, which may not hold for general neural nets (e.g., ), or still require repetitive training (e.g., [Yan and Procaccia 2021]). As a consequence, it is still an open challenge to efficiently compute data Shapley values for each sample in large datasets for general neural nets [Sim et al 2022].…”

Section: Discussionmentioning

confidence: 99%

Learning to Select Pivotal Samples for Meta Re-weighting

Wu¹,

Stein²,

Gardner³

et al. 2023

Preprint

View full text Add to dashboard Cite

Sample re-weighting strategies provide a promising mechanism to deal with imperfect training data in machine learning, such as noisily labeled or class-imbalanced data. One such strategy involves formulating a bi-level optimization problem called the meta re-weighting problem, whose goal is to optimize performance on a small set of perfect pivotal samples, called meta samples. Many approaches have been proposed to efficiently solve this problem. However, all of them assume that a perfect meta sample set is already provided while we observe that the selections of meta sample set is performancecritical. In this paper, we study how to learn to identify such a meta sample set from a large, imperfect training set, that is subsequently cleaned and used to optimize performance in the meta re-weighting setting. We propose a learning framework which reduces the meta samples selection problem to a weighted K-means clustering problem through rigorously theoretical analysis. We propose two clustering methods within our learning framework, Representation-based clustering method (RBC) and Gradient-based clustering method (GBC), for balancing performance and computational efficiency. Empirical studies demonstrate the performance advantage of our methods over various baseline methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Learning to Select Pivotal Samples for Meta Re-weighting

Wu¹,

Stein²,

Gardner³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Follow-up work has explored other explanation methods derived from the concept of Shapley value and cooperative game theory, for example, integrated gradients (Sundararajan et al, 2017), Shapley values for individual neurons (Ghorbani & Zou, 2020), or the least core (Yan & Procaccia, 2021), based on a different solution concept. Rozemberczki et al (2022) provide an in-depth overview of the cooperative game theory and numerous applications of the Shapley value in machine learning.…”

Section: Shapmentioning

confidence: 99%

Interpretable and explainable machine learning: A methods‐centric overview with concrete examples

Marcinkevičs

Vogt

2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Interpretability and explainability are crucial for machine learning (ML) and statistical applications in medicine, economics, law, and natural sciences and form an essential principle for ML model design and development. Although interpretability and explainability have escaped a precise and universal definition, many models and techniques motivated by these properties have been developed over the last 30 years, with the focus currently shifting toward deep learning. We will consider concrete examples of state-of-the-art, including specially tailored rule-based, sparse, and additive classification models, interpretable representation learning, and methods for explaining black-box models post hoc. The discussion will emphasize the need for and relevance of interpretability and explainability, the divide between them, and the inductive biases behind the presented "zoo" of interpretable models and explanation methods.

show abstract

“…We provide a brief overview of cooperative game theory (examined in details in various books [45,12]) and discuss how solution concepts in cooperative game theory have been applied in Explainable AI [15,35,36,14,56].…”

Section: Preliminariesmentioning

confidence: 99%

Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

Cornelisse¹,

Rood²,

Malinowski³

et al. 2022

Preprint

View full text Add to dashboard Cite

In many multi-agent settings, participants can form teams to achieve collective outcomes that may far surpass their individual capabilities. Measuring the relative contributions of agents and allocating them shares of the reward that promote long-lasting cooperation are difficult tasks. Cooperative game theory offers solution concepts identifying distribution schemes, such as the Shapley value, that fairly reflect the contribution of individuals to the performance of the team or the Core, which reduces the incentive of agents to abandon their team. Applications of such methods include identifying influential features and sharing the costs of joint ventures or team formation. Unfortunately, using these solutions requires tackling a computational barrier as they are hard to compute, even in restricted settings. In this work, we show how cooperative game-theoretic solutions can be distilled into a learned model by training neural networks to propose fair and stable payoff allocations. We show that our approach creates models that can generalize to games far from the training distribution and can predict solutions for more players than observed during training. An important application of our framework is Explainable AI: our approach can be used to speed-up Shapley value computations on many instances.Preprint. Under review.

show abstract

If You Like Shapley Then You’ll Love the Core

Cited by 21 publications

References 19 publications

Learning to Select Pivotal Samples for Meta Re-weighting

Learning to Select Pivotal Samples for Meta Re-weighting

Interpretable and explainable machine learning: A methods‐centric overview with concrete examples

Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

Contact Info

Product

Resources

About