Julian Padget

Cangxiong Chen, Vinay P. Namboodiri, Julian Padget

CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising result is further analysed using an attribution method-Integrated Gradients. Using this attribution method, we are able to better understand both quantitatively and qualitatively exactly the nature in which the compression affects the zero-shot recognition accuracy of this model. We evaluate this extensively on CIFAR-10 and STL-10. Our work provides the basis to understand this vulnerability of CLIP and can help us develop more effective methods to improve the robustness of CLIP and other vision-language models.

Tory Frame, Julian Padget, George Stothart et al.

Human trust is a prerequisite to trustworthy AI adoption, yet trust remains poorly understood. Trust is often described as an attitude, but attitudes cannot be reliably measured or managed. Additionally, humans frequently conflate trust in an AI system, its machine learning (ML) technology, and its other component parts. Without fully understanding the 'leap of faith' involved in trusting ML, users cannot develop intrinsic trust in these systems. A common approach to building trust is to explain a ML model's reasoning process. However, such explanations often fail to resonate with non-experts due to the inherent complexity of ML systems and explanations are disconnected from users' own (unarticulated) mental models. This work puts forward an innovative way of directly building intrinsic trust in ML, by discerning and measuring the Leap of Faith (LoF) taken when a user decides to rely on ML. The LoF matrix captures the alignment between an ML model and a human expert's mental model. This match is rigorously and practically identified by feeding the user's data and objective function into both an ML agent and an expert-validated rules-based agent: a verified point of reference that can be tested a priori against a user's own mental model. This represents a new class of neuro-symbolic architecture. The LoF matrix reveals to the user the distance that constitutes the leap of faith between the rules-based and ML agents. For the first time, we propose trust metrics that evaluate whether users demonstrate trust through their actions rather than self-reported intent and whether such trust is deserved based on outcomes. The significance of the contribution is that it enables empirical assessment and management of ML trust drivers, to support trustworthy ML adoption. The approach is illustrated through a long-term high-stakes field study: a 3-month pilot of a multi-agent sleep-improvement system.

Timotheus Kampik, Adnane Mansour, Olivier Boissier et al.

The study of autonomous agents has a long tradition in the Multiagent Systems and the Semantic Web communities, with applications ranging from automating business processes to personal assistants. More recently, the Web of Things (WoT), which is an extension of the Internet of Things (IoT) with metadata expressed in Web standards, and its community provide further motivation for pushing the autonomous agents research agenda forward. Although representing and reasoning about norms, policies and preferences is crucial to ensuring that autonomous agents act in a manner that satisfies stakeholder requirements, normative concepts, policies and preferences have yet to be considered as first-class abstractions in Web-based multiagent systems. Towards this end, this paper motivates the need for alignment and joint research across the Multiagent Systems, Semantic Web, and WoT communities, introduces a conceptual framework for governance of autonomous agents on the Web, and identifies several research challenges and opportunities.

Andreasa Morris-Martin, Marina De Vos, Julian Padget

Norm emergence is typically studied in the context of multiagent systems (MAS) where norms are implicit, and participating agents use simplistic decision-making mechanisms. These implicit norms are usually unconsciously shared and adopted through agent interaction. A norm is deemed to have emerged when a threshold or predetermined percentage of agents follow the "norm". Conversely, in normative MAS, norms are typically explicit and agents deliberately share norms through communication or are informed about norms by an authority, following which an agent decides whether to adopt the norm or not. The decision to adopt a norm by the agent can happen immediately after recognition or when an applicable situation arises. In this paper, we make the case that, similarly, a norm has emerged in a normative MAS when a percentage of agents adopt the norm. Furthermore, we posit that agents themselves can and should be involved in norm synthesis, and hence influence the norms governing the MAS, in line with Ostrom's eight principles. Consequently, we put forward a framework for the emergence of norms within a normative MAS, that allows participating agents to propose/request changes to the normative system, while special-purpose synthesizer agents formulate new norms or revisions in response to these requests. Synthesizers must collectively agree that the new norm or norm revision should proceed, and then finally be approved by an "Oracle". The normative system is then modified to incorporate the norm.

Zohreh Shams, Marina De Vos, Julian Padget et al.

Autonomous software agents operating in dynamic environments need to constantly reason about actions in pursuit of their goals, while taking into consideration norms which might be imposed on those actions. Normative practical reasoning supports agents making decisions about what is best for them to (not) do in a given situation. What makes practical reasoning challenging is the interplay between goals that agents are pursuing and the norms that the agents are trying to uphold. We offer a formalisation to allow agents to plan for multiple goals and norms in the presence of durative actions that can be executed concurrently. We compare plans based on decision-theoretic notions (i.e. utility) such that the utility gain of goals and utility loss of norm violations are the basis for this comparison. The set of optimal plans consists of plans that maximise the overall utility, each of which can be chosen by the agent to execute. We provide an implementation of our proposal in Answer Set Programming, thus allowing us to state the original problem in terms of a logic program that can be queried for solutions with specific properties. The implementation is proven to be sound and complete.

Fatemeh Jahedpari, Marina De Vos, Sattar Hashemi et al.

We propose the Artificial Continuous Prediction Market (ACPM) as a means to predict a continuous real value, by integrating a range of data sources and aggregating the results of different machine learning (ML) algorithms. ACPM adapts the concept of the (physical) prediction market to address the prediction of real values instead of discrete events. Each ACPM participant has a data source, a ML algorithm and a local decision-making procedure that determines what to bid on what value. The contributions of ACPM are: (i) adaptation to changes in data quality by the use of learning in: (a) the market, which weights each market participant to adjust the influence of each on the market prediction and (b) the participants, which use a Q-learning based trading strategy to incorporate the market prediction into their subsequent predictions, (ii) resilience to a changing population of low- and high-performing participants. We demonstrate the effectiveness of ACPM by application to an influenza-like illnesses data set, showing ACPM out-performs a range of well-known regression models and is resilient to variation in data source quality.