paper-with-me

Papers

Exact and Consistent Interpretation of Piecewise Linear Models Hidden behind APIs: A Closed Form Solution

2019-06-17 · Zicun Cong, Lingyang Chu, Lanjun Wang, Xia Hu, Jian Pei

More and more AI services are provided through APIs on cloud where predictive models are hidden behind APIs. To build trust with users and reduce potential application risk, it is important to interpret how such predictive models hidden behind APIs make their decisions. The biggest challenge of interpreting such predictions is that no access to model parameters or training data is available. Existing works interpret the predictions of a model hidden behind an API by heuristically probing the response of the API with perturbed input instances. However, these methods do not provide any guarantee on the exactness and consistency of their interpretations. In this paper, we propose an elegant closed form solution named OpenAPI to compute exact and consistent interpretations for the family of Piecewise Linear Models (PLM), which includes many popular classification models. The major idea is to first construct a set of overdetermined linear equation systems with a small set of perturbed instances and the predictions made by the model on those instances. Then, we solve the equation systems to identify the decision features that are responsible for the prediction on an input instance. Our extensive experiments clearly demonstrate the exactness and consistency of our method.

📄 PDF Abstract BibTeX arXiv:1906.06857

Code (1)

researchcode2/OpenAPI 공식 구현 pytorch

Tasks

Form

Similar Papers 제목 키워드 기반

Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution

2018-02-17 · Lingyang Chu, Xia Hu, Juhua Hu, Lanjun Wang 외

Strong intelligent machines powered by deep neural networks are increasingly deployed as black boxes to make decisions in risk-sensitive domains, such as finance and medical. To reduce potential risk and build trust with…

Form

Better Neural Network Expressivity: Subdividing the Simplex

2025-05-20 · Egor Bakaev, Florestan Brunck, Christoph Hertrich, Jack Stade 외

This work studies the expressivity of ReLU neural networks with a focus on their depth. A sequence of previous works showed that $\lceil \log_2(n+1) \rceil$ hidden layers are sufficient to compute all continuous piecewis…

The Self-Simplifying Machine: Exploiting the Structure of Piecewise Linear Neural Networks to Create Interpretable Models

2020-12-02 · William Knauth

Today, it is more important than ever before for users to have trust in the models they use. As Machine Learning models fall under increased regulatory scrutiny and begin to see more applications in high-stakes situation…

Piecewise linear activations substantially shape the loss surfaces of neural networks

2020-03-27 · ICLR 2020 1 · Fengxiang He, Bohan Wang, DaCheng Tao

Understanding the loss surface of a neural network is fundamentally important to the understanding of deep learning. This paper presents how piecewise linear activation functions substantially shape the loss surfaces of …

Tailored max-out networks for learning convex PWQ functions

2022-06-14 · Dieter Teichrib, Moritz Schulze Darup

Convex piecewise quadratic (PWQ) functions frequently appear in control and elsewhere. For instance, it is well-known that the optimal value function (OVF) as well as Q-functions for linear MPC are convex PWQ functions. …