Selected Publications

You can also find my articles on my Google Scholar profile.

Prot2Text: Multimodal Protein’s Function Generation with GNNs and Transformers

Hadi Abdine, Michail Chatzianastasis, Costas Bouyioukos, Michalis Vazirgiannis
Published: AAAI 2024, Spotlight at DGM4H Neurips 2023 and AI4Science Neurips 2023

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-decoder framework, our model effectively integrates diverse data types including proteins' sequences, structures, and textual annotations. Read more

Explainable Multilayer Graph Neural Network for Cancer Gene Prediction

Michail Chatzianastasis, Michalis Vazirgiannis, Zijun Zang
Published: Bioinformatics, Oxford Academic

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. Read more

Neural Architecture Search with Multimodal Fusion Methods for Diagnosing Dementia

Michail Chatzianastasis, Loukas Ilias, Dimitris Askounis, Michalis Vazirgiannis
Published: ICASSP 2023

We propose a multimodal deep learning approach to combine speech and text modalities for recognizing Alzheimer’s dementia (AD) using Neural Architecture Search. Read more

Graph Ordering Attention Networks

Michail Chatzianastasis, Johannes Lutzeyer, George Dasoulas, Michalis Vazirgiannis
Published: AAAI 2023

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. Read more

Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations

Giannis Nikolentzos, Michail Chatzianastasis, Michalis Vazirgiannis
Published: AISTATS 2023

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 hierarchy corresponds to a tree, to learn these representations, we capitalize on recent advances in the field of hyperbolic neural networks. Read more

Supervised Attention Using Homophily in Graph Neural Networks

Michail Chatzianastasis, Giannis Nikolentzos, Michalis Vazirgiannis
Published: ICANN 2023

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. Read more

Mass Enhanced Node Embeddings for Drug Repurposing

Michail Chatzianastasis, Giannis Nikolentzos, Michalis Vazirgiannis
Published: ICML 2022 Workshop on Computational Biology and 12th EETN Conference on Artificial Intelligence (SETN 2022)

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 its embedding. Read more

Graph-based Neural Architecture Search with Operation Embeddings

Michail Chatzianastasis, George Dasoulas, Georgios Siolas, Michalis Vazirgiannis
Published: ICCV 2021 Workshop on Neural Architectures: Past, Present and Future

We propose the replacement of fixed operator encoding with learnable representations in the optimization process. Read more