PGR Seminar with Dhananjay Saikumar

The next PGR seminar is taking place this Friday 25th April at 2PM in JC 1.33a

Below are the Title and Abstract for Dhananjay’s talk – Please do come along if you are able.

Title: Signal Collapse in One-Shot Pruning: When Sparse Models Fail to Distinguish Neural Representations

Abstract: The deep learning breakthrough in 2012, marked by AlexNet’s success on the ImageNet challenge, ushered in an era of increasingly large neural networks. Modern models now hold tens of millions to billions of parameters, enabling remarkable capabilities but creating serious challenges for deployment in real-world, resource-constrained environments. This has led to growing interest in model compression, with network pruning emerging as a widely adopted method to reduce computational and memory demands. Iterative pruning—based on repeated prune-retrain cycles—can retain accuracy but becomes infeasible at scale due to high computational cost. One-shot pruning, which removes parameters in a single step without retraining, offers a more scalable alternative but often results in severe accuracy degradation. For instance, pruning 80% of the parameters from RegNetX-32GF (a 100M+ parameter model) drops ImageNet accuracy from 80% to 1%, rendering the model unusable. This talk uncovers a new and fundamental bottleneck behind such failures: signal collapse, a previously overlooked phenomenon that disrupts the network’s ability to distinguish between inputs. To address this, a simple and efficient method called REFLOW is introduced, enabling sparse networks to recover strong performance without retraining or gradient computation. On RegNetX-32GF, REFLOW lifts accuracy from 1% to 73% at 80% sparsity—in under 15 seconds. These findings reframe the challenges of one-shot pruning and open new opportunities for practical and efficient deployment of deep learning models.

Doors Open @ Computer Science, St Andrews on Thursday 1 May 2025, 10am-4pm (drop in)

We are holding a Doors Open event on Thursday, 1 May 202,5 and would love for you and your colleagues to visit us at this event.  

Our school is growing, and we want to make sure we are listening to organisations locally, nationally, and internationally. Our hope is that the day is a chance to share and discuss some of the exciting projects going on by our staff and students. We’d love to hear about what you are doing and see if there are any interesting ways to work together.  

We have created an events webpage with details and outlines of the projects which will be on show; we are adding more every day (Doors Open @ CS). We will also have our Hot Tattie sessions upstairs in 1.33b at various times during the day. 

So we can plan refreshments, it would be great if you could register: Doors Open @ Computer Science 2025  

If you have any questions, please get in touch. 

We are hiring a Professor in Artificial Intelligence

The University of St Andrews wishes to make an appointment to the Johann and Gaynor Rupert Chair in Artificial Intelligence in the School of Computer Science.

You will be an outstanding scholar of international standing in Artificial Intelligence with a proven track record of securing significant grant funding and leading high-quality externally funded research projects. The successful candidate will be expected to have a range of interests, be able to work across disciplines, and strengthen and complement existing work within the School to make an outstanding contribution to the field’s advancement through research outputs.

See full advert here: Professor in Artificial Intelligence (Chair) – AC2605LS

PGR Seminar with Leonid Nosovitsky + Xinya Gong

The next PGR seminar is taking place this Friday 11th April at 2PM in JC 1.33a

Below are the Titles and Abstracts for Leonid and Xinya’s talks – Please do come along if you are able.

Leonid Nosovitsky

Title: Bridging Theory and Practice: Advancing Multiparty Session Types for Industry Use

Abstract: Multiparty Session Types (MPST) provide a typing discipline for communication protocols. They allow to statically check that a code implementation conforms to a specified protocol; they can also verify that a protocol satisfies many safety properties like liveness and deadlock freedom, which are crucial in concurrent communicating systems.  Despite huge improvements in MPST research, different extensions have limitations.  For example, one of extensions is crash-handling. This branch was motivated by lack of network reliability to make MPST framework more applicable and usable in industrial scenarios. The crash-semantics theory introduced by Barwell et al. does not involve any constraints relaxations, which makes it very intricate for adoption in practical scenarios.  Our project concentrates on addressing usability limitations to make MPST more integrable into industrial applications.

Xinya Gong

Title and Abstract TBC

Thanks to Dr Nnamdi Ekwe-Ekwe

Staff gathered in the coffee area of Jack Cole on Thursday 3rd April to bid farewell to Dr Nnamdi Ekwe-Ekwe on his departure from the University.

Nnamdi had been at our University since he was 21 and spent most of his university life here. Nnamdi arrived in St Andrews in 2016 to complete his Masters and PhD here and subsequently took up a lecture position in 2022 in the School of Computer Science.

The School would like to thank Nnamdi for his contributions to the School. He will be missed by all and we wish him the best of luck in his next venture!

PGR Seminar with Zihan Zhang + Berné Nortier

The next PGR seminar is taking place this Friday 4th April at 2PM in JC 1.33a

Below are the Titles and Abstracts for Zihan and Berné’s talks – Please do come along if you are able.

Zihan Zhang

Title: FedOptima: Optimizing Resource Utilization in Federated Learning

Abstract: Federated learning (FL) systems facilitate distributed machine learning across a server and multiple devices. However, FL systems have low resource utilization limiting their practical use in the real world. This inefficiency primarily arises from two types of idle time: (i) task dependency between the server and devices, and (ii) stragglers among heterogeneous devices. We propose FedOptima, a resource-optimized FL system designed to simultaneously minimize both types of idle time; existing systems do not eliminate or reduce both at the same time. FedOptima offloads the training of certain layers of a neural network from a device to server using three innovations. First, devices operate independently of each other using asynchronous aggregation to eliminate straggler effects, and independently of the server by utilizing auxiliary networks to minimize idle time caused by task dependency. Second, the server performs centralized training using a task scheduler that ensures balanced contributions from all devices, improving model accuracy. Third, an efficient memory management mechanism on the server increases scalability of the number of participating devices. Four state-of-the-art offloading-based and asynchronous FL methods are chosen as baselines. Experimental results show that compared to the best results of the baselines on convolutional neural networks and transformers on multiple lab-based testbeds, FedOptima (i) achieves higher or comparable accuracy, (ii) accelerates training by 1.9x to 21.8x, (iii) reduces server and device idle time by up to 93.9% and 81.8%, respectively, and (iv) increases throughput by 1.1x to 2.0x.

Berné Nortier

Title: Shortest paths and optimal transport in higher-order systems

Abstract: One of the defining features of complex networks is the connectivity properties that we observe emerging from local interactions. Nevertheless, not all networks describe interactions which are merely pairwise. Recently, different frameworks for modelling non-dyadic, higher-order, interactions have been proposed, garnering much attention. Of these, hypergraphs have emerged as a versatile and powerful tool to model such higher-order networks. However, the connectivity properties of real-world hypergraphs remain largely understudied. A first, data-driven, work introduces a measure to characterise higher-order connectivity and quantify the relevance of non-dyadic ties for efficient shortest paths in a diverse set of empirical networks with and without temporal information. The analysis presents a nuanced picture.

A second work (in progress) considers higher-order simplicial networks within the context of optimal transport, where shortest paths do not always lead to optimal resource allocation. We extend the existing framework to the higher-order setting to explore to what degree this additional degree of freedom influences the flux of resources in a system of interest.

Distinguished Lecture Series 2025

This years Distinguished Lecture series was delivered yesterday ( Tuesday 1st April) by Professor Arthur Zimek, University of Southern Denmark in Odense, Denmark.

In his talk on, ‘Data Mining and the “Curse of Dimensionality”’ he considered the challenges of the “curse” from the perspective of data mining. In Talk 1, he discussed the “curse” in more detail, identifying relevant aspects or problems. In Talk 2, he considered clustering facing these problems and discussed some strategies and example methods for subspace clustering. In Talk 3, he discussed outlier detection, considering strategies for improved efficiency, effectiveness, and subspace outlier detection.

PGR Seminar with Joe Loughney

The next PGR seminar is taking place this Friday 28th March at 2PM in JC 1.33a

Below are the Title and Abstract for Joe’s talk – Please do come along if you are able.

Title: Flexible-Order Symmetry Breaking in the Subgraph Isomorphism Problem

Abstract: The Subgraph Isomorphism Problem has many applications, including bioinformatics, computer vision and graph databases. Current state-of-the-art solvers using constraints programming techniques can handle cases with up to 1000 pattern vertices and 10,000 target vertices. We explore various approaches to variable and value symmetry breaking in the problem (and viable strategies to combine the two), implemented in the Glasgow Subgraph Solver, and introduce the notion of ‘flexible ordering’ on symmetry breaking constraints.

Repairing a Commodore PET 4032

Jason Jaques explains the various repairs needed on the Commodore PET 4032 in his YouTube video 

The computer was reported to be exhibiting a troubling screen wobble, an intermittent keyboard, and a broken cassette unit. However, on initial inspection, the unit was actually entirely non-functional. As the machine had been imported from the USA, the computer was expecting a ~117 V, 60 Hz mains supply. When used previously, with a step-down transformer, the screen had shown a significant wobble. Unfortunately, the unit was now entirely dead. Initial exploration indicated that it may have been plugged directly into the UK 240 V 50 Hz supply. Fortunately, while the fuse had been sacrificed, the machine had survived. Once powered up, again with a step-down transformer, the unit’s own power supply was indeed causing significant interference for the built-in display. To resolve the screen wobble, it was eventually decided to replace the transformer with a modern switching power supply. The keyboard suffered from the common hardening of the carbon pads, which made most of the keys inoperable. This was resolved by resurfacing the contacts to restore conductivity. Equally, the cassette unit was brought back to life by a minor repair to an intermittent power connection. Once operational, the unit was “tested” by (among other things) playing a quick round of Satoshi Matsuoka’s Space Invaders, loaded from cassette as demonstrated in this video.

Additional links: Commodore PET Schematics: https://www.zimmers.net/anonftp/pub/c…

Vintage Computer Federation Forums: https://forum.vcfed.org/

MOS 6502 Pinout (by Bill Bertram / Pixel8): https://en.m.wikipedia.org/wiki/File:…

FactSet Talk – Insights into Prompt Engineering 25th March

On Tuesday the 25th of March, FactSet will be visiting the School of Computer Science. They will be doing a talk on Insights into Prompt Engineering, before hosting a networking and recruitment session with pizza. This is taking place in JC1.33 A/B from 3:00pm to 5:00pm. This is a free event to attend for all.

They are recruiting for their paid software engineer externship, paid software engineer internship and graduate software engineer roles. The externship is from the 7th to 19th July in London. This is a two-week program with hands-on experience working with Software Engineering teams. The software engineering summer internship is a 12-week program in summer, with interns joining an existing team at FactSet in London. The graduate program begins in September in London.

Hope to see you all there!