Yeskendir Koishekenov

University of Amsterdam. Amsterdam, Netherlands.

prof_pic.jpeg

Hello! Welcome to my personal webpage.

I have recently graduated from master’s program in AI at the University of Amsterdam.

I have ~3 years of industry machine learning experience, acquired after obtaining my undergraduate degree. My research works were published in venues like ECCV, AAAI, ICLR, ICCV, and ReScience. I have broad research interests in Machine Learning including Natural Language Processing, Geometric Deep Learning, Graph Neural Networks, etc.

I am looking for full-time opportunities starting in Fall 2023.

news

Aug 31, 2023 I completed the Master’s degree in Artificial Intelligence at the University of Amsterdam with the distinction of cum laude.
Jul 31, 2023 Our work “Geometric Contrastive Learning” has been accepted for oral presentaion to 4th Visual Inductive Priors for Data-Efficient Deep Learning Workshop at ICCV 2023 held in Paris, France.
May 2, 2023 Our work “Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model” has been accepted to ACL 2023 held in Toronto, Canada.
May 1, 2023 I am attending ICLR 2023 in Kigali, Rwanda in person to present our paper “An Exploration of Conditioning Methods in Graph Neural Networks”.
Mar 6, 2023 Our paper “An Exploration of Conditioning Methods in Graph Neural Networks” was accepted to Machine Learning for Drug Discovery workshop at ICLR 2023.
Feb 6, 2023 Started working as a TA at “Information Retrieval 1” course for master’s students at the University of Amsterdam (until April 30th).
Feb 2, 2023 Our work “Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model” was featured by Cohere AI in their curated list of the top NLP papers of January 2023.
Nov 30, 2022 My paper entitled “Reducing Over-smoothing in Graph Neural Networks using Relational Embeddings” has been accepted to the AAAI 2023 Workshop on Deep Learning on Graphs: Methods and Applications (DLG-AAAI 2023).

selected publications

  1. ICCV
    Geometric Contrastive Learning
    Yeskendir Koishekenov, Sharvaree Vadgama*, Ricardo Valperga*, and 1 more author
    In ICCV 2023 - Visual Inductive Priors for Data-Efficient Deep Learning workshop (Oral), Oct 2023
  2. ACL
    Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model
    Yeskendir Koishekenov, Alexandre Berard, and Vassilina Nikoulina
    In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023
  3. ICLR
    An Exploration of Conditioning Methods in Graph Neural Networks
    Yeskendir Koishekenov, and Erik J Bekkers
    In ICLR 2023 - Machine Learning for Drug Discovery workshop, May 2023
  4. AAAI
    Reducing Over-smoothing in Graph Neural Networks Using Relational Embeddings
    Yeskendir Koishekenov
    Accepted to The Ninth International Workshop on Deep Learning on Graphs: Method and Applications (DLG-AAAI’23), Feb 2023