News
PGR Seminar with Mustafa Abdelwahed and Maria Andrei
The next PGR seminar is taking place this Friday 6th December at 2PM in JC 1.33a
Below is a title and Abstract for Mustafa and Maria’s talks – Please do come along if you are able.
Mustafa Abdelwahed:
Title: Behaviour Planning: A toolbox for diverse planning
Abstract:
Diverse planning approaches are utilised in real-world applications like risk management, automated streamed data analysis, and malware detection. These approaches aim to create diverse plans through a two-phase process. The first phase generates plans, while the second selects a subset of plans based on a diversity model. A diversity model is a function that quantifies the diversity of a given set of plans based on a provided distance function.
Unfortunately, existing diverse planning approaches do not account for those models when generating plans and struggle to explain why any two plans are different.
Existing diverse planning approaches do not account for those models when generating plans, hence struggle to explain why any two plans are different, and are limited to classical planning.
To address such limitations, we introduce Behaviour Planning, a novel toolbox that creates diverse plans based on customisable diversity models and can explain why two plans are different concerning such models.
Maria Andrei:
Title: Leveraging Immersive Technology to Enhance Climate Communication, Education & Action
Abstract: Climate change represents one of the most pressing challenges of our time, not only in its environmental impacts, but also as a pivotal science communication problem. Despite widespread scientific consensus on the causes and mitigation strategies for climate change, public understanding remains deeply fragmented and polarized. This disconnect hinders the collective action required from individuals, organizations, and policymakers to combat global warming effectively. My research explores the potential of immersive technologies to bridge the gap between scientific knowledge and public understanding by leveraging experiential learning experiences to inspire the attitudinal and behavioural shifts necessary to address climate change.
PGR Seminar with Zhongliang Guo
The next PGR seminar is taking place this Friday at 2PM in JC 1.33a
Below is a title and Abstract for Zhongliang’s talk– Please do come along if you are able.
Title: Adversarial Attack as a Defense: Preventing Unauthorized AI Generation in Computer Vision
Abstract: Adversarial attack is a technique that generate adversarial examples by adding imperceptible perturbations to clean images. These adversarial perturbations, though invisible to human eyes, can cause neural networks to produce incorrect outputs, making adversarial examples a significant security concern in deep learning. While previous research has primarily focused on designing powerful attacks to expose neural network vulnerabilities or using them as baselines for robustness evaluation, our work takes a novel perspective by leveraging adversarial examples to counter malicious uses of machine learning. In this seminar, I will present two of our recent works in this direction. First, I will introduce the Locally Adaptive Adversarial Color Attack (LAACA), which enables artists to protect their artwork from unauthorized neural style transfer by embedding imperceptible perturbations that significantly degrade the quality of style transfer results. Second, I will discuss our Posterior Collapse Attack (PCA), a grey-box attack method that disrupts unauthorized image editing based on Stable Diffusion by exploiting the common VAE structure in latent diffusion models. Our research demonstrates how adversarial examples, traditionally viewed as a security threat, can be repurposed as a proactive defense mechanism against the misuse of generative AI, contributing to the responsible development and deployment of these powerful technologies.
AI Seminar Wednesday 27th November – Lars Kotthoff
We have another exciting AI seminar coming up on Wednesday 27th November at 1pm.
This time our speaker is an alumnus!
When? 27/11/24, 1pm
Where? JCB 1.33B
Who? Lars Kotthoff
Lars Kotthoff is the Templeton Associate Professor of Computer Science, Founding Adjunct Faculty at the School of Computing, and a Presidential Faculty Fellow at the University of Wyoming. His research in foundational AI and Machine Learning as well as applications of AI in other areas (in particular Materials Science) has been widely published and recognized. Lars is a senior member of the Association for the Advancement of AI and the Association of Computing Machinery.
What?
Title: AI for Materials Science: Tuning Laser-Induced Graphene Production
Abstract: AI and machine learning have advanced the state of the art in many application domains. We present an application to materials science; in particular, we use surrogate models with Bayesian optimization for automated parameter tuning to optimize the fabrication of laser-induced graphene. This process allows to create thin conductive lines in thin layers of insulating material, enabling the development of next-generation nano-circuits. This is of interest for example for in-space manufacturing. We are able to achieve improvements of up to a factor of two compared to existing approaches in the literature and to what human experts are able to achieve, in a reproducible manner. Our implementation is based on the open-source mlr and mlrMBO frameworks and generalizes to other applications.
PGR Seminar with Carla Davesa Sureda
The next PGR seminar is taking place this Friday 22nd November at 2PM in JC 1.33a
Below is a Title and Abstract for Carla’s talk – Please do come along if you are able.
Title:
Towards High-Level Modelling in Automated Planning
Abstract:
Planning is a fundamental activity, arising frequently in many contexts, from daily tasks to industrial processes. The planning task consists of selecting a sequence of actions to achieve a specified goal from specified initial conditions. The Planning Domain Definition Language (PDDL) is the leading language used in the field of automated planning to model planning problems. Previous work has highlighted the limitations of PDDL, particularly in terms of its expressivity. Our interest lies in facilitating the handling of complex problems and enhancing the overall capability of automated planning systems. Unified-Planning is a Python library offering high-level API to specify planning problems and to invoke automated planners. In this paper, we present an extension of the UP library aimed at enhancing its expressivity for high-level problem modelling. In particular, we have added an array type, an expression to count booleans, and the allowance for integer parameters in actions. We show how these facilities enable natural high-level models of three classical planning problems.
Doughnuts will be available! 🍩
Fully funded PhD scholarship in Algorithms for Data Science
Lead supervisor: Dr Peter Macgregor
Application deadline: 1 March 2025
Project description:
Modern data science and machine learning applications involve datasets with millions of data points and hundreds of dimensions. For example, deep learning pipelines produce massive vector datasets representing text, image, audio and other data types. The analysis of such datasets with classical algorithms often requires significant time and/or computational resources which may not be available in many applications.
This motivates the development of a new generation of fast algorithms for data analysis, running in linear or sub-linear time and often producing an approximate result rather than an exact one. Moreover, the dataset may change over time, requiring dynamic algorithms which handle updates efficiently.
This project will tackle aspects of the design, analysis, and implementation of algorithms for processing large dynamic datasets, with the aim to develop new algorithms with state-of-the-art practical performance and/or theoretical guarantees. This could involve performing new analysis of existing algorithms, designing new algorithms with provable guarantees, or implementing heuristic algorithms with state-of-the-art empirical performance.
Possible Directions
Potential areas of research, depending on the interests of the candidate include:
- Developing improved nearest-neighbour search algorithms (e.g., based on kd-trees, HNSW, locality-sensitive hashing).
- Exploring any connection between hierarchical clustering algorithms and nearest-neighbour search algorithms.
- Creating new dynamic or hierarchical clustering algorithms (e.g. based on spectral clustering or DBSCAN).
- Creating dynamic algorithms for numerical linear algebra. For example, maintaining the PCA of a dynamically changing dataset.
- Any other project in the area of algorithmic data science and machine learning.
Applicants should have a strong interest in the mathematical analysis of algorithms, knowledge of topics in discrete mathematics and linear algebra, and some familiarity with existing algorithms for data analysis and machine learning. Strong programming skills would also be desirable.
The scholarship:
We have one fully-funded scholarship available, starting in September 2025. The scholarship covers all tuition fees irrespective of country of origin and includes a stipend valued at £19,705 per annum. More details of the scholarship can be found here: https://blogs.cs.st-andrews.ac.uk/csblog/2024/10/24/phd-studentships-available-for-2025-entry/, but please note the different application deadline.
Eligibility criteria:
We are looking for highly motivated research students keen to be part of a diverse and supportive research community. Applicants must hold a good Bachelor’s or Master’s degree in Computer Science, or a related area appropriate for the topic of this PhD.
International applications are welcome. We especially encourage female applicants and underrepresented minorities to apply. The School of Computer Science was awarded the Athena SWAN Silver award for its sustained progression in advancing equality and representation, and we welcome applications from those suitably qualified from all genders, all races, ethnicities and nationalities, LGBT+, all or no religion, all social class backgrounds, and all family structures to apply for our postgraduate research programmes.
To apply:
Interested applicants can contact Peter Macgregor with an outline proposal.
Full instructions for the formal application process
The deadline for applications is 1 March 2025.
AI Seminar Tuesday 19th November – Francesco Leofante
The School is hosting an AI seminar on Tuesday 19th November at 11am in JCB1.33A/B
Our speaker is Francesco Leofante from Imperial College London.
Title:
Robustness issues in algorithmic recourse.
Abstract:
Counterfactual explanations (CEs) are advocated as being ideally suited to providing algorithmic recourse for subjects affected by the predictions of machine learning models. While CEs can be beneficial to affected individuals, recent work has exposed severe issues related to the robustness of state-of-the-art methods for obtaining CEs. Since a lack of robustness may compromise the validity of CEs, techniques to mitigate this risk are in order. In this talk we will begin by introducing the problem of (lack of) robustness, discuss its implications and present some recent solutions we developed to compute CEs with robustness guarantees.
Bio:
Francesco is an Imperial College Research Fellow affiliated with the Centre for Explainable Artificial Intelligence at Imperial College London. His research focuses on safe and explainable AI, with special emphasis on counterfactual explanations and their robustness. Since 2022, he leads the project “ConTrust: Robust Contrastive Explanations for Deep Neural Networks”, a four-year effort devoted to the formal study of robustness issues arising in XAI. More details about Francesco and his research can be found at https://fraleo.github.io/.
PGR Seminar with Daniel Wyeth and Ferdia McKeogh
The next PGR seminar is taking place this Friday 15th November at 2PM in JC 1.33a
Below is a Title and Abstract for Daniel’s and Ferdia’s talks – Please do come along if you are able.
Daniel:
Deep Priors: Integrating Domain Knowledge into Deep Neural Networks
Deep neural networks represent the state of the art for learning complex functions purely from data. There are however problems, such as medical imaging, where data is limited, and effective training of such networks is difficult. Moreover, this requirement for large datasets represents a deficiency compared to human learning, which is able harness prior understanding to acquire new concepts with very few examples. My work looks at methods for integrating domain knowledge into deep neural networks to guide training so that fewer examples are required. In particular I explore probabilistic atlases and probabilistic graphical models as representations for this prior information, architectures which enable networks to use these, and the application of these to problems in medical image understanding.
Ferdia:
“Lessons Learned From Emulating Architectures”
Automatically generating fast emulators from formal architecture specifications avoids the error-prone and time-consuming effort of manually implementing an emulator. The key challenge is achieving high performance from correctness-focused specifications; extracting relevant functional semantics and performing aggressive optimisations. In this talk I will present my work thus far, and reflect on some of the unsuccessful paths of research.
Doughnuts will be available! 🍩
The Power of Tech in Sustainability, Inclusion, & Community: Mind and Matter 2024
The North Haugh campus was brimming with bubbling experiments, interactive activities, and research displays as St Andrews welcomed in its Mind and Matter Festival 2024 on 27th October 2024.
As a festival dedicated to inspiring creativity and curiosity from the lens of various disciplines, we were thrilled to see three of our very own researchers from the School of Computer Science presenting their latest research and subject passions to the wider community.
Starting off, Dr Kirsty Ross (Industrial Liaison) was exhibiting ‘We Can Edit: St Andrews on WikiCommons’. This was badged as a Cloud Activity (one of the six groups or categories of activities participants could engage with) which was all about transforming the perspective of how we understand ourselves and how we use our knowledge:
“What we’re doing today is encouraging folks to sign up to Wiki and then go on a listed building hunt round St Andrews and add photos of those buildings to WikiCommons.”
The project is a part of the Inclusion, Diversity, Equity, and Accessibility (IDEA) Network, and engages with “the increasing interest in Wiki and open knowledge.” Founded in April 2021 (alongside her colleague Dr Abd Alsattar Ardati who she had never actually met face-to-face due to the pandemic), Dr Ross recalls how it all started as a way of “getting people involved, whether that’s research, teaching, or knowledge exchange.” As the Wikimedia project is more than just Wikipedia, containing various sister projects such as Wikidata, Wikimedia Commons, etc, Dr Ross remarked that this project is all about “increasing the impact of our research and making it accessible to everyone” through their active participation.
In line with this collective effort, Dr Ross noted that it’s presence at a festival such as Mind and Matter helps put a “human face” to research that could equally fascinate experts, as well as those who are new to the topic. Most importantly though, it reminds us that “our audience is not just an empty vessel that turn up and you fill them with knowledge, and that’s our job done. They come with their own interests, background, and passion, and it’s about finding the hook that works for each person that you talk to.” A wonderful reminder that innovative research engagement begins from something as simple as the conversations being held around us.
On a similar note, Dr. Dharini Balasubramaniam (Senior Lecturer) displayed her Cloud Activity ‘Once upon a time there was the web’ poster which shared research insights into intergenerational approaches for making digital services more inclusive.
“When we started looking,” Dr. Balasubramaniam commented, “we very quickly realized, it’s not something that computer scientists can solve by themselves. We must work with all the stakeholders who are involved, including the older adults who are disadvantaged by the proliferation of the technologies, as well as the people who support them.” This includes collaborating with local groups and organisations here at St Andrews such as St Andrews Public Library, Haydays Fife, North East Fife Community Hub, and more. It also entails contributing time to festivals like Mind and Matter because co-creating solutions (participatory design) hugely revolves around talking to people as “not everyone will have the same attitude, abilities, or reactions to digital technology. Therefore, we cannot make any assumptions about how accessible something is to a particular person without actually talking to them.”
The project arose from Dr. Balasubramaniam’s interest in representing digital ethics within software architectures, which extends to broader thinking about the social and cultural effect of our technological systems. It then led to important conversations being had between herself, her family, and older people within the town of St Andrews about where they had felt left behind, demonstrating that “a lot of work needed to be done for it.” A crucial part of this work involves increasing software literacy. In other words, “making people aware of how digital technologies work and the impact of the choices they might make.” It also includes “making service providers aware of the particular challenges that marginalized groups might face in access. What if you are an older person and you have physical or cognitive impairments? What if you are part of a minority group in some way? If you have a certain disability, or if you have moved here from another part of the world and the language used isn’t necessarily accessible to you?”
Dr. Balasubramaniam remarked that presenting this research to the public is both exciting and humbling: “It reminds me of the big picture and why we are doing this, and what’s been really inspiring is how keen people are to engage with researchers and to contribute. That’s the most amazing thing.”
Turning to a Tree Activity, panels dedicated to connecting us with the natural world and sustainable futures, Dr. Alan Miller (Lecturer) exhibited ‘Virtual Reality for Sustainable Development’ which allowed participants to interactively contemplate sustainability, cultural preservation, and the effects of climate change.
“At this festival we are showing work concerned with two things — representations of the past and future. One is making digital reconstructions of the world heritage site, St Kilda, as it was in 1819. Another is raising awareness about the effects of climate change through the representation of Paradise Bay in Antarctica by showing the situation today and how it’s likely to change as a result of climate change, as well as demonstrating the potential future of Glasgow based upon James Rae’s work that shows a ten meter rise in sea-level which is consistent with the levels of carbon that we have in the atmosphere at the moment.”
Dr. Miller explained that it was the efforts of many being shown at Mind and Matter, including PhD work being conducted by Maria Andrei (virtual reality and climate change) and Sharon Pisani (sustainable development through digital tourism and heritage), as well as his own interests in applying 3D technologies to experiences of the past and future in order to promote the United Nations 2023 Agenda for Sustainable Development. The project is based on the idea of experiential learning being a deep form of education that can help overcome “psychological distance, whereby people maybe don’t appreciate statistics and numbers of what the impact of climate change will be” and therefore if they can “experience what it might be like, it could make it easier to achieve the sort of behavioural changes we need in order to holt climate change.”
While climate crisis and sustainability are large scale issues that can often feel out of our reach, engaging with it within our local community can hugely enable researchers and participants alike to consider its significance. Dr. Miller best described it as applying “practice-led research, whereby we try to develop initiatives in the community and understand its impact,” which when presented to local and non-local audiences at a festival, open a feedback loop of communication on what works and what does not.
“I suppose the most exciting part is you put together your research but then it’s when people come along and interact with it, and maybe it changes the way they think about the world or the way in which they carry themselves within it. It’s nice to know that the research we do has some impact on people’s lives.”
There are coherent themes of inclusivity, accessibility, and community being explored within the Department of Computer Science demonstrating how tech and data can be used for good. What is most appealing is that the research exhibited at the Mind and Matter Festival are actively increasing their scope throughout the university and St Andrews.
Dr. Kirsty Ross commented on the IDEA Network wanting to scale their work through a ESPRC (Engineering & Physical Sciences Research Council) grant; Dr. Dharini Balasubramaniam mentioned the project being in the process of setting up a monthly digital support session in local community spaces, as well as volunteer opportunities readily available; and Dr. Alan Miller is a part of the Open Virtual Worlds Group which hosts various workshops, collaborations, and projects that allow those interested in immersive technology for the preservation and promotion of heritage to get involved.
It is thrilling to see where computer science is taking us! What remains now is to anticipate what innovative initiatives will be fore fronted at next year’s festival and throughout the school over the next academic year.
By Nina Globerson, Science Communicator for the School of Computer Science
PhD Viva Success: Yingxue Fu
On behalf of the school, we would like to congratulate Yingxue Fu supervised by Mark-Jan Nederhoff, who has passed their PhD viva with minor corrections.
Thanks to Dr Alice Tonilo who was internal examiner and Professor Amir Zeldes from Georgetown University as external examiner.
Many congratulations to Yingxue!