Despite their ubiquitous use, Shapley value feature attributions can be misleading due to feature interaction in both model and data. We propose an alternative attribution approach, Shapley Sets, which awards value to sets of features. Shapley Sets attributes to each non-separable variable group their combined value for a particular prediction. We show that Shapley Sets is equivalent to the Shapley value over the transformed feature set and thus benefits from the same axioms of fairness. Shapley Sets is value function agnostic and we show theoretically and experimentally how Shapley Sets avoids pitfalls associated with Shapley value based alternatives and are particularly advantageous for data types with complex dependency structure.

We describe a proof-of-principle implementation of a system for drawing melodies that abstracts away from a note-level input representation via melodic contours. The aim is to allow users to express their musical intentions without requiring prior knowledge of how notes fit together melodiously. Current approaches to controllable melody generation often require users to choose parameters that are static across a whole sequence, via buttons or sliders. In contrast, our method allows users to quickly specify how parameters should change over time by drawing a contour.

In supervised learning, low quality annotations lead to poorly performing classification and detection models, while also rendering evaluation unreliable. This is particularly apparent on temporal data, where annotation quality is affected by multiple factors. For example, in the post-hoc self-reporting of daily activities, cognitive biases are one of the most common ingredients. In particular, reporting the start and duration of an activity after its finalisation may incorporate biases introduced by personal time perceptions, as well as the imprecision and lack of granularity due to time rounding. Here we propose a method to model human biases on temporal annotations and argue for the use of soft labels. Experimental results in synthetic data show that soft labels provide a better approximation of the ground truth for several metrics. We showcase the method on a real dataset of daily activities.

Explainable artificial intelligence and interpretable machine learning are research fields growing in importance. Yet, the underlying concepts remain somewhat elusive and lack generally agreed definitions. While recent inspiration from social sciences has refocused the work on needs and expectations of human recipients, the field still misses a concrete conceptualisation. We take steps towards addressing this challenge by reviewing the philosophical and social foundations of human explainability, which we then translate into the technological realm. In particular, we scrutinise the notion of algorithmic black boxes and the spectrum of understanding determined by explanatory processes and explainees' background knowledge. This approach allows us to define explainability as (logical) reasoning applied to transparent insights (into black boxes) interpreted under certain background knowledge - a process that engenders understanding in explainees. We then employ this conceptualisation to revisit the much disputed trade-off between transparency and predictive power and its implications for ante-hoc and post-hoc explainers as well as fairness and accountability engendered by explainability. We furthermore discuss components of the machine learning workflow that may be in need of interpretability, building on a range of ideas from human-centred explainability, with a focus on explainees, contrastive statements and explanatory processes. Our discussion reconciles and complements current research to help better navigate open questions - rather than attempting to address any individual issue - thus laying a solid foundation for a grounded discussion and future progress of explainable artificial intelligence and interpretable machine learning. We conclude with a summary of our findings, revisiting the human-centred explanatory process needed to achieve the desired level of algorithmic transparency.

Academic trade requires juggling multiple variants of the same content published in different formats: manuscripts, presentations, posters and computational notebooks. The need to track versions to accommodate for the write--review--rebut--revise life-cycle adds another layer of complexity. We propose to significantly reduce this burden by maintaining a single source document in a version-controlled environment (such as git), adding functionality to generate a collection of output formats popular in academia. To this end, we utilise various open-source tools from the Jupyter scientific computing ecosystem and operationalise selected software engineering concepts. We offer a proof-of-concept workflow that composes Jupyter Book (an online document), Jupyter Notebook (a computational narrative) and reveal.js slides from a single markdown source file. Hosted on GitHub, our approach supports change tracking and versioning, as well as a transparent review process based on the underlying code issue management infrastructure. An exhibit of our workflow can be previewed at https://so-cool.github.io/you-only-write-thrice/.

In online applications with streaming data, awareness of how far the training or test set has shifted away from the original dataset can be crucial to the performance of the model. However, we may not have access to historical samples in the data stream. To cope with such situations, we propose a novel method, Continual Density Ratio Estimation (CDRE), for estimating density ratios between the initial and current distributions ($p/q_t$) of a data stream in an iterative fashion without the need of storing past samples, where $q_t$ is shifting away from $p$ over time $t$. We demonstrate that CDRE can be more accurate than standard DRE in terms of estimating divergences between distributions, despite not requiring samples from the original distribution. CDRE can be applied in scenarios of online learning, such as importance weighted covariate shift, tracing dataset changes for better decision making. In addition, (CDRE) enables the evaluation of generative models under the setting of continual learning. To the best of our knowledge, there is no existing method that can evaluate generative models in continual learning without storing samples from the original distribution.

The use of episodic memories in continual learning has been shown to be effective in terms of alleviating catastrophic forgetting. In recent studies, several gradientbased approaches have been developed to make more efficient use of compact episodic memories, which constrain the gradients resulting from new samples with those from memorized samples, aiming to reduce the diversity of gradients from different tasks. In this paper, we reveal the relation between diversity of gradients and discriminativeness of representations, demonstrating connections between Deep Metric Learning and continual learning. Based on these findings, we propose a simple yet highly efficient method - Discriminative Representation Loss (DRL) - for continual learning. In comparison with several state-of-theart methods, DRL shows effectiveness with low computational cost on multiple benchmark experiments in the setting of online continual learning. In the real world, we are often faced with situations where data distributions are changing over time, and we would like to update our models by new data in time, with bounded growth in system size. These situations fall under the umbrella of "continual learning", which has many practical applications, such as recommender systems, retail supply chain optimization, and robotics (Lesort et al., 2019; Diethe et al., 2018; Tian et al., 2018).

Interpretable representations are the backbone of many black-box explainers. They translate the low-level data representation necessary for good predictive performance into high-level human-intelligible concepts used to convey the explanation. Notably, the explanation type and its cognitive complexity are directly controlled by the interpretable representation, allowing to target a particular audience and use case. However, many explainers that rely on interpretable representations overlook their merit and fall back on default solutions, which may introduce implicit assumptions, thereby degrading the explanatory power of such techniques. To address this problem, we study properties of interpretable representations that encode presence and absence of human-comprehensible concepts. We show how they are operationalised for tabular, image and text data, discussing their strengths and weaknesses. Finally, we analyse their explanatory properties in the context of tabular data, where a linear model is used to quantify the importance of interpretable concepts.

Systems based on artificial intelligence and machine learning models should be transparent, in the sense of being capable of explaining their decisions to gain humans' approval and trust. While there are a number of explainability techniques that can be used to this end, many of them are only capable of outputting a single one-size-fits-all explanation that simply cannot address all of the explainees' diverse needs. In this work we introduce a model-agnostic and post-hoc local explainability technique for black-box predictions called LIMEtree, which employs surrogate multi-output regression trees. We validate our algorithm on a deep neural network trained for object detection in images and compare it against Local Interpretable Model-agnostic Explanations (LIME). Our method comes with local fidelity guarantees and can produce a range of diverse explanation types, including contrastive and counterfactual explanations praised in the literature. Some of these explanations can be interactively personalised to create bespoke, meaningful and actionable insights into the model's behaviour. While other methods may give an illusion of customisability by wrapping, otherwise static, explanations in an interactive interface, our explanations are truly interactive, in the sense of allowing the user to "interrogate" a black-box model. LIMEtree can therefore produce consistent explanations on which an interactive exploratory process can be built.

Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are model-agnostic and are post-hoc (i.e., can be retrofitted). The Local Interpretable Model-agnostic Explanations (LIME) algorithm is often mistakenly unified with a more general framework of surrogate explainers, which may lead to a belief that it is the solution to surrogate explainability. In this paper we empower the community to "build LIME yourself" (bLIMEy) by proposing a principled algorithmic framework for building custom local surrogate explainers of black-box model predictions, including LIME itself. To this end, we demonstrate how to decompose the surrogate explainers family into algorithmically independent and interoperable modules and discuss the influence of these component choices on the functional capabilities of the resulting explainer, using the example of LIME.