Posts by Collection
portfolio
publications
Graph-based Neural Architecture Search with Operation Embeddings
Michail Chatzianastasis, George Dasoulas, Georgios Siolas, Michalis Vazirgiannis
We propose the replacement of fixed operator encoding with learnable representations in the optimization process.
Mass Enhanced Node Embeddings for Drug Repurposing
Michail Chatzianastasis, Giannis Nikolentzos, Michalis Vazirgiannis
We propose a node embedding algorithm for the problem of drug repurposing. The proposed algorithm learns node representations that capture the influence of nodes in the biological network by learning a mass term for each node along with ...
Supervised Attention Using Homophily in Graph Neural Networks
Michail Chatzianastasis, Giannis Nikolentzos, Michalis Vazirgiannis
We propose a new technique that can be incorporated into any graph attention model to encourage higher attention scores between nodes that share the same class label.
Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations
Giannis Nikolentzos, Michail Chatzianastasis, Michalis Vazirgiannis
In this paper, we define a distance function between nodes which is based on the hierarchy produced by the WL algorithm, and propose a model that learns representations which preserve those distances between nodes. Since the emerging hie...
Graph Ordering Attention Networks
Michail Chatzianastasis, Johannes Lutzeyer, George Dasoulas, Michalis Vazirgiannis
We introduce the Graph Ordering Attention (GOAT) layer, a novel GNN component that learns local node orderings via an attention mechanism and processes the ordered representations using a recurrent neural network aggregator.
Neural Architecture Search with Multimodal Fusion Methods for Diagnosing Dementia
Michail Chatzianastasis, Loukas Ilias, Dimitris Askounis, Michalis Vazirgiannis
We propose a multimodal deep learning approach to combine speech and text modalities for recognizing Alzheimer’s dementia (AD) using Neural Architecture Search.
Explainable Multilayer Graph Neural Network for Cancer Gene Prediction
Michail Chatzianastasis, Michalis Vazirgiannis, Zijun Zang
We introduce an Explainable Multilayer Graph Neural Network (EMGNN) approach to identify cancer genes by leveraging multiple gene-gene interaction networks and pan-cancer multi-omics data.
Prot2Text: Multimodal Protein’s Function Generation with GNNs and Transformers
Hadi Abdine, Michail Chatzianastasis, Costas Bouyioukos, Michalis Vazirgiannis
We propose Prot2Text, which predicts a protein function’s in a free text style, moving beyond the conventional binary or categorical classifications. By combining Graph Neural Networks(GNNs) and Large Language Models(LLMs), in an encoder...
Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment
Xiao Fei, Michail Chatzianastasis, Sarah Almeida Carneiro, Hadi Abdine, Lawrence P. Petalidis, Michalis Vazirgiannis
We propose Prot2Text, which predicts a protein function’s in a free text style, moving beyond the conventional binary or categorical classifications. By combining Graph Neural Networks(GNNs) and Large Language Models(LLMs), in an encoder...
talks
teaching
Polytechnic Executive Education Program
MSC course, École Polytechnique · Paris, France · Nov 2021
MSC DATA MANAGEMENT & ARTIFICIAL INTELLIGENCE, INSEEC
MSC course, INSEEC Business School · Paris, France · Feb 2022
Msc in Machine Learning (MVA), Ecole Polytechnique
Advanced learning for text and graph data(ALTEGRAD), MVA · Paris, France · Nov 2022
Course on Engineering Track at Ecole Polytechnique
INF581A: Advanced Deep Learning, · Paris, France · Jan 2024