67 citations · 262 across the 30 of their papers we have counts for
33 papers
Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization
Fernando Acero, Parisa Zehtabi, Nicolas Marchesotti +3
Portfolio optimization involves determining the optimal allocation of portfolio assets in order to maximize a given investment objective. Traditionally, some form of mean-variance…
REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values
Shubham Sharma, Sanghamitra Dutta, Emanuele Albini +3
Feature selection is a crucial step in building machine learning models. This process is often achieved with accuracy as an objective, and can be cumbersome and computationally exp…
On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
Emanuele Albini, Shubham Sharma, Saumitra Mishra +2
Explainable Artificial Intelligence (XAI) has received widespread interest in recent years, and two of the most popular types of explanations are feature attributions, and counterf…
SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features
Sanjay Kariyappa, Leonidas Tsepenekas, Freddy Lécué +1
The SHAP framework provides a principled method to explain the predictions of a model by computing feature importance. Motivated by applications in finance, we introduce the Top-k…
Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates
Kyle Mana, Fernando Acero, Stephen Mak +4
Discrete optimization belongs to the set of -hard problems, spanning fields such as mixed-integer programming and combinatorial optimization. A current standard appro…
GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations
Dan Ley, Saumitra Mishra, Daniele Magazzeni
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods prominent in fairness, recourse and model understanding. The m…
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
Faisal Hamman, Erfaun Noorani, Saumitra Mishra +2
There is an emerging interest in generating robust counterfactual explanations that would remain valid if the model is updated or changed even slightly. Towards finding robust coun…
Bayesian Hierarchical Models for Counterfactual Estimation
Natraj Raman, Daniele Magazzeni, Sameena Shah
Counterfactual explanations utilize feature perturbations to analyze the outcome of an original decision and recommend an actionable recourse. We argue that it is beneficial to pro…
Learn to explain yourself, when you can: Equipping Concept Bottleneck Models with the ability to abstain on their concept predictions
Joshua Lockhart, Daniele Magazzeni, Manuela Veloso
The Concept Bottleneck Models (CBMs) of Koh et al. [2020] provide a means to ensure that a neural network based classifier bases its predictions solely on human understandable conc…
Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning
Danial Dervovic, Nicolas Marchesotti, Freddy Lecue +1
We introduce a family of interpretable machine learning models, with two broad additions: Linearised Additive Models (LAMs) which replace the ubiquitous logistic link function in G…
Towards learning to explain with concept bottleneck models: mitigating information leakage
Joshua Lockhart, Nicolas Marchesotti, Daniele Magazzeni +1
Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint. Then a downstream model uses these predi…
Feature Importance for Time Series Data: Improving KernelSHAP
Mattia Villani, Joshua Lockhart, Daniele Magazzeni
Feature importance techniques have enjoyed widespread attention in the explainable AI literature as a means of determining how trained machine learning models make their prediction…
Robust Counterfactual Explanations for Tree-Based Ensembles
Sanghamitra Dutta, Jason Long, Saumitra Mishra +2
Counterfactual explanations inform ways to achieve a desired outcome from a machine learning model. However, such explanations are not robust to certain real-world changes in the u…
Global Counterfactual Explanations: Investigations, Implementations and Improvements
Dan Ley, Saumitra Mishra, Daniele Magazzeni
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. Howeve…
Asynchronous Collaborative Learning Across Data Silos
Tiffany Tuor, Joshua Lockhart, Daniele Magazzeni
Machine learning algorithms can perform well when trained on large datasets. While large organisations often have considerable data assets, it can be difficult for these assets to…
Explaining Preference-driven Schedules: the EXPRES Framework
Alberto Pozanco, Francesca Mosca, Parisa Zehtabi +2
Scheduling is the task of assigning a set of scarce resources distributed over time to a set of agents, who typically have preferences about the assignments they would like to get.…
Optimal Admission Control for Multiclass Queues with Time-Varying Arrival Rates via State Abstraction
Marc Rigter, Danial Dervovic, Parisa Hassanzadeh +3
We consider a novel queuing problem where the decision-maker must choose to accept or reject randomly arriving tasks into a no buffer queue which are processed by identical ser…
A Survey on the Robustness of Feature Importance and Counterfactual Explanations
Saumitra Mishra, Sanghamitra Dutta, Jason Long +1
There exist several methods that aim to address the crucial task of understanding the behaviour of AI/ML models. Arguably, the most popular among them are local explanations that f…
How Robust are Limit Order Book Representations under Data Perturbation?
Yufei Wu, Mahmoud Mahfouz, Daniele Magazzeni +1
The success of machine learning models in the financial domain is highly reliant on the quality of the data representation. In this paper, we focus on the representation of limit o…
Counterfactual Shapley Additive Explanations
Emanuele Albini, Jason Long, Danial Dervovic +1
Feature attributions are a common paradigm for model explanations due to their simplicity in assigning a single numeric score for each input feature to a model. In the actionable r…
Towards Robust Representation of Limit Orders Books for Deep Learning Models
Yufei Wu, Mahmoud Mahfouz, Daniele Magazzeni +1
The success of deep learning-based limit order book forecasting models is highly dependent on the quality and the robustness of the input data representation. A significant body of…
Graph Reasoning with Context-Aware Linearization for Interpretable Fact Extraction and Verification
Neema Kotonya, Thomas Spooner, Daniele Magazzeni +1
This paper presents an end-to-end system for fact extraction and verification using textual and tabular evidence, the performance of which we demonstrate on the FEVEROUS dataset. W…
Counterfactual Explanations for Arbitrary Regression Models
Thomas Spooner, Danial Dervovic, Jason Long +3
We present a new method for counterfactual explanations (CFEs) based on Bayesian optimisation that applies to both classification and regression models. Our method is a globally co…
Contrastive Explanations of Plans Through Model Restrictions
Benjamin Krarup, Senka Krivic, Daniele Magazzeni +3
In automated planning, the need for explanations arises when there is a mismatch between a proposed plan and the user's expectation. We frame Explainable AI Planning in the context…