Department of CS newsletter

Our List of Issues

You may recall that around 6 months ago we created a list of issues that were affecting many of the activities we are engaged in. Sarah Mulholland has worked with the appropriate PS teams to generate a set of helpful responses associated with each. You can see our original list and responses via the link below. Please feel free to comment in the appropriate box if needs be.

https://livemanchesterac-my.sharepoint.com/:w:/g/personal/ruth_maddocks_manchester_ac_uk/ESU6QCZwdXBJlg_nVFlYkSUBX37eZS7Oh0sCzT3To8NCTQ?e=P6xdJH

Training and Leadership Courses

Those of you who are interested in developing your leadership skills may like to sign up for some of the University’s training courses. These would be particularly useful to do if you’re interested in moving into a leadership role in the future - they’re also a good way to meet other colleagues across our University:

https://www.staffnet.manchester.ac.uk/staff-learning-and-development/learning-pathways/leading-managing-and-supervising-at-the-university-of-manchester/our-development-programmes/

https://www.staffnet.manchester.ac.uk/staff-learning-and-development/programmes-and-courses/

Congratulations to Jiaoyan

Finally, congratulations to Jiaoyan on his recently funded EPSRC New Investigator Award “OntoEm: Semantic Embedding for Ontologies”. The project will focus on representation of an ontology with its semantics (partially) kept in a vector space. Such vector representations of the entities, a.k.a. embeddings, can directly benefit many prediction tasks in ontology construction such as ontology completion and alignment, augment the combination of symbolic knowledge and machine learning for addressing challenges like sample and explanation shortage, and can be applied to science and engineering problems where ontologies and knowledge graphs are used for data modelling, such as protein function prediction with the Gene Ontology.

Best wishes

Andrew

Hi, 

I am the High Fliers Technology Research Ambassador for the University of Manchester. My job is to get final year students to sign up to their portal so that they can participate in surveys conducted by leading companies like Google, Amazon, Microsoft, Goldman Sachs,  JP Morgan etc. in the UK’s technology industry. Students get paid £10 an hour for participating in the surveys and all the need to do is a 30 sec sign up to receive the relevant surveys. It is very important that they don’t forget to validate their university email IDs. Would it possible to add this to the Wednesday Waggle focusing on all final year CS students (in 3^rd year in a 3-year degree and in 4^th year in a 4-year degree)? If possible, I can provide a few graphics to go with the announcement. I’d be really grateful if you could help me with this :)

Thanks and regards,

Anisha Sahu

We are delighted to invite you to The Institute for Data Science and AI Seminar with Petar Veličković, Staff Research Scientist, Google DeepMind and Affiliated Lectureship at the University of Cambridge 

The Institute for Data Science and AI’s Seminars, bring together researchers from across the broad fields within data science and artificial intelligence to explore the latest advances and to discuss important topical questions being posed by society around the use of data science and AI. 
 
The seminar, taking place on Friday 27th October at The University of Manchester, is a fantastic opportunity for you to learn about innovative research within the realm of Data Science and AI, and network with peers. 

Decoupling the Input Graph and the Computational Graph: The most important unsolved problem in graph representation learning 

When deploying graph neural networks, we often make a seemingly innocent assumption: that the input graph we are given is the ground-truth. However, as this talk will unpack, this is often not the case: even when the graphs are perfectly correct, they may be severely suboptimal for completing the task at hand. This will introduce us to a rich and vibrant area of graph rewiring, which is experiencing a renaissance in recent times. Petar will discuss some of the most representative works, including two of our own contributions, one of which won the Best Paper Award at the Graph Learning Frontiers Workshop at NeurIPS'22. 

Agenda: 

13:45 - Registration and Arrival 

14:00 - Welcome and introductions 

14:10 - Petar Veličković, Staff Research Scientist, Google DeepMind and Affiliated Lectureship at the University of Cambridge 

14:45 - Q&A 

15:00 - Networking 

15:30 - Event close 

Places at limited so we advise you to secure your place now to avoid disappointment. We hope to see you there! 

https://www.eventbrite.co.uk/e/732844566827?aff=oddtdtcreator 

Bio: Petar Veličković is a Research Scientist at DeepMind. He holds a PhD degree from the University of Cambridge (obtained under the supervision of Pietro Liò), with prior collaborations at Nokia Bell Labs and Mila. His current research interests broadly involve devising neural network architectures that operate on nontrivially structured data (such as graphs), and their applications in algorithmic reasoning and computational biology. 

Petar has published his work in these areas at both machine learning venues (ICLR, NeurIPS-W, ICML-W) and biomedical venues and journals (Bioinformatics, PLOS One, JCB, PervasiveHealth). In particular, he is the first author of Graph Attention Networks, a popular convolutional layer for graphs, and Deep Graph Infomax, a scalable local/global unsupervised learning pipeline for graphs. His research has been featured in media outlets such as ZDNet. Additionally, he has co-organised workshops on Graph Representation Learning at ICLR 2019 and NeurIPS 2019.