A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Efficiently explains model outputs using HSIC, a dependence measure.
Proposes a method for explaining black-box models with nested feature attributions.
We interpret black box predictive models using causal attribution.
WCAM assesses neural network reliability by attributing decisions to wavelet scales.
tDB removes unfairness from black-box models using probability theory.
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an…
Multi-party machine learning leaks global dataset properties even with black-box access.
Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting…
PredDiff measures prediction changes while marginalizing features, offering new insights into interaction effects.
Adapts IG for better feature attributions and robustness.
Our work investigates disagreement in neural network feature attribution methods.
New method for interpreting financial model risks.
Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary information or make the system more vulnerable. This work shows that such attri…
Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differenti…
Complex models are commonly used in predictive modeling. In this paper we present R packages that can be used to explain predictions from complex black box models and attribute parts of these predictions to input features. We introduce two new approaches and corresponding packages for such attribution, namely live and …
Automates UI implementation from designer images.
New method interprets deep neural networks for better recommendation system understanding.
We consider black-box global optimization of time-consuming-to-evaluate functions on behalf of a decision-maker (DM) whose preferences must be learned. Each feasible design is associated with a time-consuming-to-evaluate vector of attributes and each vector of attributes is assigned a utility by the DM's utility functi…
Most companies utilize demographic information to develop their strategy in a market. However, such information is not available to most retail companies. Several studies have been conducted to predict the demographic attributes of users from their transaction histories, but they have some limitations. First, they focu…
Develops causal explanations for black-box classifiers.
Attributed graphs, which contain rich contextual features beyond just network structure, are ubiquitous and have been observed to benefit various network analytics applications. Graph structure optimization, aiming to find the optimal graphs in terms of some specific measures, has become an effective computational tool…
PathBoost boosts graph-level predictions using path-based features.
A number of techniques have been proposed to explain a machine learning model's prediction by attributing it to the corresponding input features. Popular among these are techniques that apply the Shapley value method from cooperative game theory. While existing papers focus on the axiomatic motivation of Shapley values…
BBRT improves molecular properties through iterative translation.
Interpretable ML methods for better decision-making with explanations.
In this paper we propose a method to obtain global explanations for trained black-box classifiers by sampling their decision function to learn alternative interpretable models. The envisaged approach provides a unified solution to approximate non-linear decision boundaries with simpler classifiers while retaining the o…
Convolutional neural network based systems have largely failed to be adopted in many high-risk application areas, including healthcare, military, security, transportation, finance, and legal, due to their highly uninterpretable "black-box" nature. Towards solving this deficiency, we teach a novel multi-task capsule net…
A new method for variable importance measures without impossible data.
CD-RCA method identifies causal relationships in prediction errors without predefined graphs.
Face recognition models can be inferred from student models, posing privacy risks.
This research discovers model architecture and training dataset characteristics through strategic input probing.
Machine learning has recently been widely adopted to address the managerial decision making problems, in which the decision maker needs to be able to interpret the contributions of individual attributes in an explicit form. However, there is a trade-off between performance and interpretability. Full complexity models a…
Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must exhibit high transparency. In this paper, to address this black-box limitation, we …
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input, known as adversarial examples, which represent a security threat for learned vision …
Signed Evidence Flow (SEF) combines fitted prediction with signed feature attributions to measure evidence conflict and stability.
Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex physical, chemical, biological and social systems. However, in most cases this comes with the disadvantage of acting as a black box, rarely pro…
Study examines XAI methods for ECG analysis to improve model transparency.
Paper introduces attacks to infer GAN training dataset properties.
The paper proposes a method to verify tree ensembles by reasoning about potential instances.
Reduces risk of model inversion by reducing sensitive feature influence.
Most accurate recommender systems are black-box models, hiding the reasoning behind their recommendations. Yet explanations have been shown to increase the user's trust in the system in addition to providing other benefits such as scrutability, meaning the ability to verify the validity of recommendations. This gap bet…
Paper proposes structured semantic perturbations to improve adversarial attacks.
A new baseline for Shapley values in MLPs considers model use.
Deep neural networks have achieved state of the art accuracy at classifying molecules with respect to whether they bind to specific protein targets. A key breakthrough would occur if these models could reveal the fragment pharmacophores that are causally involved in binding. Extracting chemical details of binding from …
CBMs improve interpretability in RUL prediction for aircraft engines.
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible a…
Study shows explanation disparities in machine learning models are influenced by data and model properties.
Proposes a Taylor framework to unify and analyze attribution methods.