arXiv subjects

Tim Miller

Publications and source records attributed to Tim Miller.

At least 55 records · Page 3Linked to original sources

arXiv2021

Fair and Responsible AI: A Focus on the Ability to Contest

As the use of artificial intelligence (AI) in high-stakes decision-making increases, the ability to contest such decisions is being recognised in AI ethics guidelines as an important safeguard for individuals. Yet, there is little guidance on how AI systems can be designed to support contestation. In this paper we explain that the design of a contestation process is important due to its impact on perceptions of fairness and satisfaction. We also consider design challenges, including a lack of transparency as well as the numerous design options that decision-making entities will be faced with. We argue for a human-centred approach to designing for contestability to ensure that the needs of decision subjects, and the community, are met.

cs.HC↗

arXiv2021

Designing for Contestation: Insights from Administrative Law

A paper presented at the Workshop on Contestability in Algorithmic Systems at CSCW 2019. Challenging algorithmic decisions is important to decision subjects, yet numerous factors can limit a person's ability to contest such decisions. We propose that administrative law systems, which were created to ensure that governments are kept accountable for their actions and decision making in relation to individuals, can provide guidance on how to design contestation systems for algorithmic decision-making.

cs.HC↗

arXiv2021

Deceptive Reinforcement Learning for Privacy-Preserving Planning

In this paper, we study the problem of deceptive reinforcement learning to preserve the privacy of a reward function. Reinforcement learning is the problem of finding a behaviour policy based on rewards received from exploratory behaviour. A key ingredient in reinforcement learning is a reward function, which determines how much reward (negative or positive) is given and when. However, in some situations, we may want to keep a reward function private; that is, to make it difficult for an observer to determine the reward function used. We define the problem of privacy-preserving reinforcement learning, and present two models for solving it. These models are based on dissimulation -- a form of deception that `hides the truth'. We evaluate our models both computationally and via human behavioural experiments. Results show that the resulting policies are indeed deceptive, and that participants can determine the true reward function less reliably than that of an honest agent.

cs.LG↗

arXiv2021

Directive Explanations for Actionable Explainability in Machine Learning Applications

This paper investigates the prospects of using directive explanations to assist people in achieving recourse of machine learning decisions. Directive explanations list which specific actions an individual needs to take to achieve their desired outcome. If a machine learning model makes a decision that is detrimental to an individual (e.g. denying a loan application), then it needs to both explain why it made that decision and also explain how the individual could obtain their desired outcome (if possible). At present, this is often done using counterfactual explanations, but such explanations generally do not tell individuals how to act. We assert that counterfactual explanations can be improved by explicitly providing people with actions they could use to achieve their desired goal. This paper makes two contributions. First, we present the results of an online study investigating people's perception of directive explanations. Second, we propose a conceptual model to generate such explanations. Our online study showed a significant preference for directive explanations ($p<0.001$). However, the participants' preferred explanation type was affected by multiple factors, such as individual preferences, social factors, and the feasibility of the directives. Our findings highlight the need for a human-centred and context-specific approach for creating directive explanations.

cs.LG↗

arXiv2021

Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI

Trust is a central component of the interaction between people and AI, in that 'incorrect' levels of trust may cause misuse, abuse or disuse of the technology. But what, precisely, is the nature of trust in AI? What are the prerequisites and goals of the cognitive mechanism of trust, and how can we promote them, or assess whether they are being satisfied in a given interaction? This work aims to answer these questions. We discuss a model of trust inspired by, but not identical to, sociology's interpersonal trust (i.e., trust between people). This model rests on two key properties of the vulnerability of the user and the ability to anticipate the impact of the AI model's decisions. We incorporate a formalization of 'contractual trust', such that trust between a user and an AI is trust that some implicit or explicit contract will hold, and a formalization of 'trustworthiness' (which detaches from the notion of trustworthiness in sociology), and with it concepts of 'warranted' and 'unwarranted' trust. We then present the possible causes of warranted trust as intrinsic reasoning and extrinsic behavior, and discuss how to design trustworthy AI, how to evaluate whether trust has manifested, and whether it is warranted. Finally, we elucidate the connection between trust and XAI using our formalization.

cs.AI↗

arXiv2020

Confederated Machine Learning on Horizontally and Vertically Separated Medical Data for Large-Scale Health System Intelligence

Health information is generally fragmented across silos. Though it is technically feasible to unite data for analysis in a manner that underpins a rapid learning healthcare system, privacy concerns and regulatory barriers limit data centralization. Machine learning can be conducted in a federated manner on patient datasets with the same set of variables, but separated across sites of care. But federated learning cannot handle the situation where different data types for a given patient are separated vertically across different organizations and when patient ID matching across different institutions is difficult. We call methods that enable machine learning model training on data separated by two or more degrees confederated machine learning. We proposed and evaluated a confederated learning to training machine learning model to stratify the risk of several diseases among when data are horizontally separated by individual, vertically separated by data type, and separated by identity without patient ID matching.

cs.LG↗

arXiv2020

Contrastive Explanation: A Structural-Model Approach

This paper presents a model of contrastive explanation using structural casual models. The topic of causal explanation in artificial intelligence has gathered interest in recent years as researchers and practitioners aim to increase trust and understanding of intelligent decision-making. While different sub-fields of artificial intelligence have looked into this problem with a sub-field-specific view, there are few models that aim to capture explanation more generally. One general model is based on structural causal models. It defines an explanation as a fact that, if found to be true, would constitute an actual cause of a specific event. However, research in philosophy and social sciences shows that explanations are contrastive: that is, when people ask for an explanation of an event -- the fact -- they (sometimes implicitly) are asking for an explanation relative to some contrast case; that is, "Why P rather than Q?". In this paper, we extend the structural causal model approach to define two complementary notions of contrastive explanation, and demonstrate them on two classical problems in artificial intelligence: classification and planning. We believe that this model can help researchers in subfields of artificial intelligence to better understand contrastive explanation.

cs.AI↗

arXiv2020

Good proctor or "Big Brother"? AI Ethics and Online Exam Supervision Technologies

This article philosophically analyzes online exam supervision technologies, which have been thrust into the public spotlight due to campus lockdowns during the COVID-19 pandemic and the growing demand for online courses. Online exam proctoring technologies purport to provide effective oversight of students sitting online exams, using artificial intelligence (AI) systems and human invigilators to supplement and review those systems. Such technologies have alarmed some students who see them as `Big Brother-like', yet some universities defend their judicious use. Critical ethical appraisal of online proctoring technologies is overdue. This article philosophically analyzes these technologies, focusing on the ethical concepts of academic integrity, fairness, non-maleficence, transparency, privacy, respect for autonomy, liberty, and trust. Most of these concepts are prominent in the new field of AI ethics and all are relevant to the education context. The essay provides ethical considerations that educational institutions will need to carefully review before electing to deploy and govern specific online proctoring technologies.

cs.CY↗

arXiv2020

Distal Explanations for Model-free Explainable Reinforcement Learning

In this paper we introduce and evaluate a distal explanation model for model-free reinforcement learning agents that can generate explanations for `why' and `why not' questions. Our starting point is the observation that causal models can generate opportunity chains that take the form of `A enables B and B causes C'. Using insights from an analysis of 240 explanations generated in a human-agent experiment, we define a distal explanation model that can analyse counterfactuals and opportunity chains using decision trees and causal models. A recurrent neural network is employed to learn opportunity chains, and decision trees are used to improve the accuracy of task prediction and the generated counterfactuals. We computationally evaluate the model in 6 reinforcement learning benchmarks using different reinforcement learning algorithms. From a study with 90 human participants, we show that our distal explanation model results in improved outcomes over three scenarios compared with two baseline explanation models.

cs.AI↗

arXiv2020

Federated pretraining and fine tuning of BERT using clinical notes from multiple silos

Large scale contextual representation models, such as BERT, have significantly advanced natural language processing (NLP) in recently years. However, in certain area like healthcare, accessing diverse large scale text data from multiple institutions is extremely challenging due to privacy and regulatory reasons. In this article, we show that it is possible to both pretrain and fine tune BERT models in a federated manner using clinical texts from different silos without moving the data.

cs.CL↗

arXiv2019

Explainable Reinforcement Learning Through a Causal Lens

Prevalent theories in cognitive science propose that humans understand and represent the knowledge of the world through causal relationships. In making sense of the world, we build causal models in our mind to encode cause-effect relations of events and use these to explain why new events happen. In this paper, we use causal models to derive causal explanations of behaviour of reinforcement learning agents. We present an approach that learns a structural causal model during reinforcement learning and encodes causal relationships between variables of interest. This model is then used to generate explanations of behaviour based on counterfactual analysis of the causal model. We report on a study with 120 participants who observe agents playing a real-time strategy game (Starcraft II) and then receive explanations of the agents' behaviour. We investigated: 1) participants' understanding gained by explanations through task prediction; 2) explanation satisfaction and 3) trust. Our results show that causal model explanations perform better on these measures compared to two other baseline explanation models.

cs.LG↗

arXiv2019

A mass-dependent slope of the galaxy size-mass relation out to z~3: further evidence for a direct relation between median galaxy size and median halo mass

We reassess the galaxy size-mass relation out to z~3 using a new definition of size and a sample of >29,000 galaxies from the 3D-HST, CANDELS, and COSMOS-DASH surveys. Instead of the half-light radius r_50 we use r_80, the radius containing 80% of the stellar light. We find that the r_80 -- M_star relation has the form of a broken power law, with a clear change of slope at a pivot mass M_p. Below the pivot mass the relation is shallow (r_80 \propto M_star^0.15) and above it it is steep (r_80\propto M_star^0.6). The pivot mass increases with redshift, from log(M_p/M_sun)~ 10.2 at z=0.4 to log(M_p/M_sun)~ 10.9 at z=1.7-3. We compare these r_80-M_star relations to the M_halo-M_star relations derived from galaxy-galaxy lensing, clustering analyses, and abundance matching techniques. Remarkably, the pivot stellar masses of both relations are consistent with each other at all redshifts, and the slopes are very similar both above and below the pivot when assuming M_halo \propto r_80^3. The implied scaling factor to relate galaxy size to halo size is r_80 / R_vir = 0.047, independent of stellar mass and redshift.From redshift 0 to 1.5, the pivot mass also coincides with the mass where the fraction of star-forming galaxies is 50%, suggesting that the pivot mass reflects a transition from dissipational to dissipationless galaxy growth. Finally, our results imply that the scatter in the stellar-to-halo mass ratio is relatively small for massive halos (~0.2 dex for M_halo>10^12.5 M_sun).

astro-ph.GA↗

arXiv2019

Let's Make It Personal, A Challenge in Personalizing Medical Inter-Human Communication

Current AI approaches have frequently been used to help personalize many aspects of medical experiences and tailor them to a specific individuals' needs. However, while such systems consider medically-relevant information, they ignore socially-relevant information about how this diagnosis should be communicated and discussed with the patient. The lack of this capability may lead to mis-communication, resulting in serious implications, such as patients opting out of the best treatment. Consider a case in which the same treatment is proposed to two different individuals. The manner in which this treatment is mediated to each should be different, depending on the individual patient's history, knowledge, and mental state. While it is clear that this communication should be conveyed via a human medical expert and not a software-based system, humans are not always capable of considering all of the relevant aspects and traversing all available information. We pose the challenge of creating Intelligent Agents (IAs) to assist medical service providers (MSPs) and consumers in establishing a more personalized human-to-human dialogue. Personalizing conversations will enable patients and MSPs to reach a solution that is best for their particular situation, such that a relation of trust can be built and commitment to the outcome of the interaction is assured. We propose a four-part conceptual framework for personalized social interactions, expand on which techniques are available within current AI research and discuss what has yet to be achieved.

cs.AI↗

arXiv2019

What you get is what you see: Decomposing Epistemic Planning using Functional STRIPS

Epistemic planning --- planning with knowledge and belief --- is essential in many multi-agent and human-agent interaction domains. Most state-of-the-art epistemic planners solve this problem by compiling to propositional classical planning, for example, generating all possible knowledge atoms, or compiling epistemic formula to normal forms. However, these methods become computationally infeasible as problems grow. In this paper, we decompose epistemic planning by delegating reasoning about epistemic formula to an external solver. We do this by modelling the problem using \emph{functional STRIPS}, which is more expressive than standard STRIPS and supports the use of external, black-box functions within action models. Exploiting recent work that demonstrates the relationship between what an agent `sees' and what it knows, we allow modellers to provide new implementations of externals functions. These define what agents see in their environment, allowing new epistemic logics to be defined without changing the planner. As a result, it increases the capability and flexibility of the epistemic model itself, and avoids the exponential pre-compilation step. We ran evaluations on well-known epistemic planning benchmarks to compare with an existing state-of-the-art planner, and on new scenarios based on different external functions. The results show that our planner scales significantly better than the state-of-the-art planner against which we compared, and can express problems more succinctly.

cs.AI↗

arXiv2019

A Grounded Interaction Protocol for Explainable Artificial Intelligence

Explainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee and investigate the structural aspects of an interactive explanation to propose an interaction protocol. We follow a bottom-up approach to derive the model by analysing transcripts of different explanation dialogue types with 398 explanation dialogues. We use grounded theory to code and identify key components of an explanation dialogue. We formalize the model using the agent dialogue framework (ADF) as a new dialogue type and then evaluate it in a human-agent interaction study with 101 dialogues from 14 participants. Our results show that the proposed model can closely follow the explanation dialogues of human-agent conversations.

cs.AI↗

arXiv2018

Emotional Attachment Framework for People-Oriented Software

In organizational and commercial settings, people often have clear roles and workflows against which functional and non-functional requirements can be extracted. However, in more social settings, such as platforms for enhancing social interaction, successful applications are driven more by using emotional engagement than functionality, and the drivers of user engagement are difficult to identify. A key challenge is to understand people's emotional goals so that they can be incorporated into the design. This paper proposes a novel framework called the Emotional Attachment Framework, which is based on existing models and theories of emotional attachment. Its aim is to facilitate the process of getting a deeper insight into emotional goals in software engineering. To demonstrate the framework in use, emotional goals are elicited for a software application that aims to provide help for homeless people. To measure the effectiveness and efficiency of the proposed technique in this study, a series of evaluations are undertaken: a semi-controlled experiment, a comparison analysis, and domain expert and end-user evaluation. The results indicate that the Emotional Attachment Framework has the potential to give better insight during analysis of emotional goals.

cs.SE↗

arXiv2018

Emotionalism within People-Oriented Software Design

In designing most software applications, much effort is placed upon the functional goals, which make a software system useful. However, the failure to consider emotional goals, which make a software system pleasurable to use, can result in disappointment and system rejection even if utilitarian goals are well implemented. Although several studies have emphasized the importance of people's emotional goals in developing software, there is little advice on how to address these goals in the software system development process. This paper proposes a theoretically-sound and practical method by combining the theories and techniques of software engineering, requirements engineering, and decision making. The outcome of this study is the Emotional Goal Systematic Analysis Technique (EG-SAT), which facilitates the process of finding software system capabilities to address emotional goals in software design. EG-SAT is easy to learn and easy to use technique that helps analysts to gain insights into how to address people's emotional goals. To demonstrate the method in use, a two-part evaluation is conducted. First, EG-SAT is used to analyze the emotional goals of potential users of a mobile learning application that provides information about low carbon living for tradespeople and professionals in the building industry in Australia. The results of using EG-SAT in this case study are compared with a professionally-developed baseline. Second, we ran a semi-controlled experiment in which 12 participants were asked to apply EG-SAT and another technique on part of our case study. The outcomes show that EG-SAT helped participants to both analyse emotional goals and gain valuable insights about the functional and non-functional goals for addressing people's emotional goals.

cs.SE↗

arXiv2018

Explanation in Artificial Intelligence: Insights from the Social Sciences

There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to make their algorithms more understandable. Much of this research is focused on explicitly explaining decisions or actions to a human observer, and it should not be controversial to say that looking at how humans explain to each other can serve as a useful starting point for explanation in artificial intelligence. However, it is fair to say that most work in explainable artificial intelligence uses only the researchers' intuition of what constitutes a `good' explanation. There exists vast and valuable bodies of research in philosophy, psychology, and cognitive science of how people define, generate, select, evaluate, and present explanations, which argues that people employ certain cognitive biases and social expectations towards the explanation process. This paper argues that the field of explainable artificial intelligence should build on this existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics. It draws out some important findings, and discusses ways that these can be infused with work on explainable artificial intelligence.

cs.AI↗