About Me

Hi! I am Alex Mara, a recently graduated Doctor of Computer Science Engineering. Until recently, I was part of the Artificial Intelligence and Data Analytics (AIDA) research group led by Prof. Tijl De Bie at Ghent University. My research was centered around graphs. More specifically, on new vector representations for graph data that allow us to effectively and efficiently perform traditional downstream predictions tasks such as classification and inference. On this page, you can find more information about me, my research interests, publications and other activities.

Regarding my education, previous to the PhD I obtained an MSc in Computer Communication and Information Sicences (Machine Learning and Data Mining Major) from Aalto University and a BSc in Computer Engineering from the Technical University of Madrid. I graduated with honours from both programs and received several mentions and awards. You can check out my full CV here.

On my free time I like to practice sports mainly mountain biking, calisthenics and climbing. I also enjoy playing videogames both recent ones as well as the classics (P.S.: try searching for a non-existend subdomain on my website, like this one :P).

Research Interests

Representation Learning

Dimensionality Reduction

Graph Semi-supervised Learning

Big Data Analytics

Distributed Computing

Experimental Design & Evaluation


Journal Articles

Mara, A., Lijffijt, J., & De Bie, T. (2022). An Empirical Evaluation of Network Representation Learning Methods. Big Data.
Mara, A., Lijffijt, J., & De Bie, T. (2022). EvalNE: A Framework for Network Embedding Evaluation. SoftwareX, 17.
Jung, A., Hero, III, A. O., Mara, A., Jahromi, S., Heimowitz, A., & Eldar, Y. C. (2019). Semi-supervised Learning in Network-structured Data Via Total Variation Minimization. IEEE Transactions on Signal Processing, 67(24), 6256–6269.
Jung, A., Tran, N., & Mara, A. (2018). When is Network Lasso Accurate? Frontiers in Applied Mathematics and Statistics, 3, 28.

Conference Proceedings

Mara, A., Lijffijt, J., Günnemann, S., & De Bie, T. (2022). A Systematic Evaluation of Node Embedding Robustness. Proceedings of the First Learning on Graphs Conference, vol. 198, PMLR, 2022.
Adriaens, F., Mara, A., Lijffijt, J., & De Bie, T. (2020). Block-approximated Exponential Random Graphs. In 2020 IEEE 7th International Conference on Data Science and Advanced Analytics.
Mara, A., Lijffijt, J., & d. Bie, T. (2020). Benchmarking Network Embedding Models for Link Prediction: Are we Making Progress? In 2020 IEEE 7th International Conference on Data Science and Advanced Analytics.
Mara, A., Mashayekhi, Y., Lijffijt, J., & De Bie, T. (2020). CSNE: Conditional Signed Network Embedding. In Proceedings of the 29th ACM International Conference on Information Knowledge Management.
Mara, A., Lijffijt, J. De Bie, T. (2019). EvalNE : A Framework for Evaluating Network Embeddings on Link Prediction. Procceedings of EDML, (SDM).
Mara, A. & Jung, A. (2017). Recovery Conditions and Sampling Strategies for Network Lasso. In 51st Asilomar Conference on Signals, Systems and Computers. Finalist of the Asilomar 2017 best student paper contest.
Zhu, B., Mara, A., & Mozo, A. (2015). Clus: Parallel Subspace Clustering Algorithm on Spark. In T. Morzy, P. Valduriez, & L. Bellatreche (Eds.), New Trends in Databases and Information Systems.


Mara, A. (2023). Accelerating Progress in Network Representation Learning: Systematic Evaluations and New Approaches. Ghent University Press.
Mara, A. (2017). A Comparative Analysis of Graph Signal Recovery Methods for Big Data Networks. Aalto University Press, 67(24).

Teaching Experience

  • Teaching Assistant: AI Research Seminar, Ghent University, 2021
  • Teaching Assistant: Big Data Science, Ghent University, 2018/2019/2020
  • Teaching Assistant: Machine Learning Basic Principles, Aalto University, 2016
  • Teaching Assistant: Convex Optimization for Big Data, Aalto University, 2015
  • Teaching Assistant: Mathematical Analysis, Technical University of Madrid, 2011/2012/2013

Other Activities