Author name cluster

Satoshi Hara

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

1 author row

TMLR Journal 2025 Journal Article

Path-Specific Counterfactual Fairness via Dividend Correction

Daisuke Hatano
Satoshi Hara
Hiromi Arai

Counterfactual fairness is a fundamental principle in machine learning that allows the analysis of the effects of sensitive attributes in each individual decision by integrating the knowledge of causal graphs. An issue in dealing with counterfactual fairness is that unfair causal effects are often context-specific, influenced by religious, cultural, and national differences, making it difficult to create a universally applicable model. This leads to the challenge of dealing with frequent adaptation to changes in fairness assessments when localizing a model. Thus, applicability across a variety of models and efficiency becomes necessary to meet this challenge. We propose the first efficient post-process approach to achieve path-specific counterfactual fairness by adjusting a model's outputs based on a given causal graph. This approach is model-agnostic, prioritizing on flexibility and generalizability to deliver robust results across various domains and model architectures. By means of the mathematical tools in cooperative game, the Möbius inversion formula and dividends, we demonstrate that our post-process approach can be executed efficiently. We empirically show that proposed algorithm outperforms existing in-process approaches for path-specific counterfactual fairness and a post-process approach for counterfactual fairness.

PDF Details

TMLR Journal 2025 Journal Article

Variance Reduction of Stochastic Hypergradient Estimation by Mixed Fixed-Point Iteration

Naoyuki Terashita
Satoshi Hara

Hypergradient represents how the hyperparameter of an optimization problem (or inner-problem) changes an outer-cost through the optimized inner-parameter, and it takes a crucial role in hyperparameter optimization, meta learning, and data influence estimation. This paper studies hypergradient computation involving a stochastic inner-problem, a typical machine learning setting where the empirical loss is estimated by minibatches. Stochastic hypergradient estimation requires estimating products of Jacobian matrices of the inner iteration. Current methods struggle with large estimation variance because they depend on a specific sequence of Jacobian samples to estimate this product. This paper overcomes this problem by \emph{mixing} two different stochastic hypergradient estimation methods that use distinct sequences of Jacobian samples. Furthermore, we show that the proposed method enables almost sure convergence to the true hypergradient through the stochastic Krasnosel'ski\u{\i}-Mann iteration. Theoretical analysis demonstrates that, compared to existing approaches, our method achieves lower asymptotic variance bounds while maintaining comparable computational complexity. Empirical evaluations on synthetic and real-world tasks verify our theoretical results and superior variance reduction over existing methods.

PDF Details

AAAI Conference 2022 Conference Paper

Explainable and Local Correction of Classification Models Using Decision Trees

Hirofumi Suzuki
Hiroaki Iwashita
Takuya Takagi
Keisuke Goto
Yuta Fujishige
Satoshi Hara

In practical machine learning, models are frequently updated, or corrected, to adapt to new datasets. In this study, we pose two challenges to model correction. First, the effects of corrections to the end-users need to be described explicitly, similar to standard software where the corrections are described as release notes. Second, the amount of corrections need to be small so that the corrected models perform similarly to the old models. In this study, we propose the first model correction method for classification models that resolves these two challenges. Our idea is to use an additional decision tree to correct the output of the old models. Thanks to the explainability of decision trees, the corrections are describable to the end-users, which resolves the first challenge. We resolve the second challenge by incorporating the amount of corrections when training the additional decision tree so that the effects of corrections to be small. Experiments on real data confirm the effectiveness of the proposed method compared to existing correction methods.

PDF Details

NeurIPS Conference 2021 Conference Paper

Characterizing the risk of fairwashing

Ulrich Aïvodji
Hiromi Arai
Sébastien Gambs
Satoshi Hara

Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation. In this paper, we investigate the capability of fairwashing attacks by analyzing their fidelity-unfairness trade-offs. In particular, we show that fairwashed explanation models can generalize beyond the suing group (i. e. , data points that are being explained), meaning that a fairwashed explainer can be used to rationalize subsequent unfair decisions of a black-box model. We also demonstrate that fairwashing attacks can transfer across black-box models, meaning that other black-box models can perform fairwashing without explicitly using their predictions. This generalization and transferability of fairwashing attacks imply that their detection will be difficult in practice. Finally, we propose an approach to quantify the risk of fairwashing, which is based on the computation of the range of the unfairness of high-fidelity explainers.

PDF Details

AAAI Conference 2020 Conference Paper

Faking Fairness via Stealthily Biased Sampling

Kazuto Fukuchi
Satoshi Hara
Takanori Maehara

Auditing fairness of decision-makers is now in high demand. To respond to this social demand, several fairness auditing tools have been developed. The focus of this study is to raise an awareness of the risk of malicious decision-makers who fake fairness by abusing the auditing tools and thereby deceiving the social communities. The question is whether such a fraud of the decision-maker is detectable so that the society can avoid the risk of fake fairness. In this study, we answer this question negatively. We speciﬁcally put our focus on a situation where the decision-maker publishes a benchmark dataset as the evidence of his/her fairness and attempts to deceive a person who uses an auditing tool that computes a fairness metric. To assess the (un)detectability of the fraud, we explicitly construct an algorithm, the stealthily biased sampling, that can deliberately construct an evil benchmark dataset via subsampling. We show that the fraud made by the stealthily based sampling is indeed difﬁcult to detect both theoretically and empirically.

PDF Details

NeurIPS Conference 2019 Conference Paper

Data Cleansing for Models Trained with SGD

Satoshi Hara
Atsushi Nitanda
Takanori Maehara

Data cleansing is a typical approach used to improve the accuracy of machine learning models, which, however, requires extensive domain knowledge to identify the influential instances that affect the models. In this paper, we propose an algorithm that can identify influential instances without using any domain knowledge. The proposed algorithm automatically cleans the data, which does not require any of the users' knowledge. Hence, even non-experts can improve the models. The existing methods require the loss function to be convex and an optimal model to be obtained, which is not always the case in modern machine learning. To overcome these limitations, we propose a novel approach specifically designed for the models trained with stochastic gradient descent (SGD). The proposed method infers the influential instances by retracing the steps of the SGD while incorporating intermediate models computed in each step. Through experiments, we demonstrate that the proposed method can accurately infer the influential instances. Moreover, we used MNIST and CIFAR10 to show that the models can be effectively improved by removing the influential instances suggested by the proposed method.

PDF Details

AAAI Conference 2018 Conference Paper

Approximate and Exact Enumeration of Rule Models

Satoshi Hara
Masakazu Ishihata

In machine learning, rule models are one of the most popular choices when model interpretability is the primary concern. Ordinary, a single model is obtained by solving an optimization problem, and the resulting model is interpreted as the one that best explains the data. In this study, instead of ﬁnding a single rule model, we propose algorithms for enumerating multiple rule models. Model enumeration is useful in practice when (i) users want to choose a model that is particularly suited to their task knowledge, or (ii) users want to obtain several possible mechanisms that could be underlying the data to use as hypotheses for further scientiﬁc studies. To this end, we propose two enumeration algorithms: an approximate algorithm and an exact algorithm. We prove that these algorithms can enumerate models in a descending order of their objective function values approximately and exactly. We then conﬁrm our theoretical results through experiments on real-world data. We also show that, by using the proposed enumeration algorithms, we can ﬁnd several different models of almost equal quality.

PDF Details

AAAI Conference 2017 Conference Paper

Enumerate Lasso Solutions for Feature Selection

Satoshi Hara
Takanori Maehara

We propose an algorithm for enumerating solutions to the Lasso regression problem. In ordinary Lasso regression, one global optimum is obtained and the resulting features are interpreted as task-relevant features. However, this can overlook possibly relevant features not selected by the Lasso. With the proposed method, we can enumerate many possible feature sets for human inspection, thus recording all the important features. We prove that by enumerating solutions, we can recover a true feature set exactly under less restrictive conditions compared with the ordinary Lasso. We conﬁrm our theoretical results also in numerical simulations. Finally, in the gene expression and the text data, we demonstrate that the proposed method can enumerate a wide variety of meaningful feature sets, which are overlooked by the global optima.

PDF Details