Avatar

Zekarias Tilahun

Postdoc in Machine Learning

KTH Royal Institute of Technology

Kistagången 16, 164 40, Kista
zekarias[at]kth[dot]se

Recent News

March 25, 2020:

Our paper, "Gossip and Attend: Context-sensitive Graph Representation Learning" is accepted for the International AAAI Conference on Web and Social Media (ICWSM 2020).

June 1, 2019:

I have started my Postdoc at the School of Electrical Engineering and Computer Science in the Royal Institute of Technology (KTH), Stockholm, Sweden

April 29, 2019:

I have received my PhD from the University of Trento

October 17, 2018:

Our paper, "Network Agnostic Cascade Prediction in Online Social Networks", has won the best paper award at the 5th SNAMS'18, IEEE conference.

Bio

I'm a postdoc in Decentralized Machine Learning. Before, I did my PhD in Computer Science with a Machine Learning specialization and I had the previledge to work under the supervision of Prof. Montresor.
I'm generally interested in Machine Learning, Natural Language Processing, and Social Network Analysis. My PhD research was mainly on Graph Embedding (aka - Network Representation Learning - NRL) and Information Diffusion Analysis. More concretely, i have explored how we can use data from information diffusion events and node attributes in order to learn high-quality embedding of nodes. This is particularly useful in cases where the network under consideration is noisy. For example when it has missing information, such as social links between nodes.

Professional Activities

  1. Reviewer: Elsevier Pattern Recognition Journal

  2. Reviewer: IEEE Transactions on Knowledge and Data Engineering

  3. Reviewer: Computing Journal

  4. PC Member: The Sixth IEEE International Conference on Social Networks Analysis, Management and Security SNAMS'19

  5. PC Member: The Fifth International Conference on Machine Learning, Optimization, and Data Science, LOD'19

  6. PC Member: The Fourth International Conference on Machine Learning, Optimization, and Data Science, LOD'18

Skills

  1. Machine learning and cluster computing Frameworks
    • Tensorflow, PyTorch, Keras, Apache Spark, Hadoop, Pandas, Numpy, and more
  2. Programming Languages
    • Python, Java, JavaScript, C++, Scala, R
    • Recently learning Go
  3. Data Visualization
    • Plotly - in JavaScript, Python, R
    • ggplot - in R
    • Dash, seaborn, matplotlib - in Python

Fore more details, checkout my CV