no code implementations • ACL 2022 • Moussa Kamal Eddine, Guokan Shang, Antoine Tixier, Michalis Vazirgiannis
While traditional natural language generation metrics are fast, they are not very reliable.
1 code implementation • 15 Nov 2024 • Hugo Schnoering, Michalis Vazirgiannis
This paper introduces a large scale dataset in the form of a transactions graph representing transactions between Bitcoin users along with a set of tasks and baselines.
no code implementations • 13 Nov 2024 • Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Amine Mohamed Aboussalah, Michalis Vazirgiannis
Graph Neural Networks (GNNs) have shown great promise in tasks like node and graph classification, but they often struggle to generalize, particularly to unseen or out-of-distribution (OOD) data.
no code implementations • 8 Nov 2024 • Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Fragkiskos D. Malliaros, Michalis Vazirgiannis
Graph Neural Networks (GNNs), which are nowadays the benchmark approach in graph representation learning, have been shown to be vulnerable to adversarial attacks, raising concerns about their real-world applicability.
1 code implementation • 7 Nov 2024 • Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Michalis Vazirgiannis
Graph Shift Operators (GSOs), such as the adjacency and graph Laplacian matrices, play a fundamental role in graph theory and graph representation learning.
1 code implementation • 27 Oct 2024 • Yassine Abbahaddou, Johannes F. Lutzeyer, Michalis Vazirgiannis
In most previous methods, a heterogeneous graph, containing both word and document nodes, is constructed using the entire corpus and a GNN is used to classify document nodes.
no code implementations • 25 Oct 2024 • Christos Xypolopoulos, Guokan Shang, Xiao Fei, Giannis Nikolentzos, Hadi Abdine, Iakovos Evdaimon, Michail Chatzianastasis, Giorgos Stamou, Michalis Vazirgiannis
Large language models have evolved to process multiple modalities beyond text, such as images and audio, which motivates us to explore how to effectively leverage them for graph machine learning tasks.
no code implementations • 17 Oct 2024 • Virgile Rennard, Christos Xypolopoulos, Michalis Vazirgiannis
Large language models (LLMs) inherit biases from their training data and alignment processes, influencing their responses in subtle ways.
no code implementations • 26 Sep 2024 • Konstantinos Skianis, Giannis Nikolentzos, Michalis Vazirgiannis
This success of LLMs has also motivated their use in graph-related tasks.
no code implementations • 26 Sep 2024 • Guokan Shang, Hadi Abdine, Yousef Khoubrane, Amr Mohamed, Yassine Abbahaddou, Sofiane Ennadir, Imane Momayiz, Xuguang Ren, Eric Moulines, Preslav Nakov, Michalis Vazirgiannis, Eric Xing
We introduce Atlas-Chat, the first-ever collection of LLMs specifically developed for dialectal Arabic.
no code implementations • 16 Sep 2024 • Nikolaos Nakis, Chrysoula Kosma, Giannis Nikolentzos, Michalis Chatzianastasis, Iakovos Evdaimon, Michalis Vazirgiannis
Autoencoders based on Graph Neural Networks (GNNs) have garnered significant attention in recent years for their ability to extract informative latent representations, characterizing the structure of complex topologies, such as graphs.
1 code implementation • 26 Jun 2024 • Roman Bresson, Giannis Nikolentzos, George Panagopoulos, Michail Chatzianastasis, Jun Pang, Michalis Vazirgiannis
In recent years, Graph Neural Networks (GNNs) have become the de facto tool for learning node and graph representations.
no code implementations • 20 Jun 2024 • Michail Chatzianastasis, Yang Zhang, George Dasoulas, Michalis Vazirgiannis
Protein representation learning aims to learn informative protein embeddings capable of addressing crucial biological questions, such as protein function prediction.
1 code implementation • 31 May 2024 • Amr AlKhatib, Henrik Boström, Michalis Vazirgiannis
The results also indicate that using CEGA in combination with either SHAP or Anchors consistently leads to a higher fidelity compared to using LIME as the local explanation technique.
no code implementations • 17 May 2024 • Virgile Rennard, Guokan Shang, Michalis Vazirgiannis, Julie Hunter
We introduce an extractive summarization system for meetings that leverages discourse structure to better identify salient information from complex multi-party discussions.
1 code implementation • 27 Apr 2024 • Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis, Henrik Boström
In this work, we theoretically define the concept of expected robustness in the context of attributed graphs and relate it to the classical definition of adversarial robustness in the graph representation learning literature.
2 code implementations • 3 Mar 2024 • Iakovos Evdaimon, Giannis Nikolentzos, Christos Xypolopoulos, Ahmed Kammoun, Michail Chatzianastasis, Hadi Abdine, Michalis Vazirgiannis
Graph generation has emerged as a crucial task in machine learning, with significant challenges in generating graphs that accurately reflect specific properties.
no code implementations • 1 Mar 2024 • Hugo Schnoering, Pierre Porthaux, Michalis Vazirgiannis
This process often employs heuristics grounded in the practices and behaviors of these entities.
1 code implementation • 21 Feb 2024 • Sofiane Ennadir, Yassine Abbahaddou, Johannes F. Lutzeyer, Michalis Vazirgiannis, Henrik Boström
Successful combinations of our NoisyGNN approach with existing defense techniques demonstrate even further improved adversarial defense results.
1 code implementation • 5 Feb 2024 • Giannis Nikolentzos, Siyun Wang, Johannes Lutzeyer, Michalis Vazirgiannis
We then propose a new machine learning model for tabular data, the so-called Graph Neural Machine (GNM), which replaces the MLP's directed acyclic graph with a nearly complete graph and which employs a synchronous message passing scheme.
1 code implementation • 8 Dec 2023 • Virgile Rennard, Guokan Shang, Damien Grari, Julie Hunter, Michalis Vazirgiannis
In this paper, we present a dataset of French political debates for the purpose of enhancing resources for multi-lingual dialogue summarization.
no code implementations • 21 Nov 2023 • Hugo Schnoering, Michalis Vazirgiannis
This study delves deeply into the open-source implementations of these protocols, aiming to develop refined heuristics for identifying their transactions on the blockchain.
1 code implementation • 20 Nov 2023 • Yanzhu Guo, Guokan Shang, Virgile Rennard, Michalis Vazirgiannis, Chloé Clavel
With the increasing amount of problematic peer reviews in top AI conferences, the community is urgently in need of automatic quality control measures.
1 code implementation • 16 Nov 2023 • Yanzhu Guo, Guokan Shang, Michalis Vazirgiannis, Chloé Clavel
This study investigates the consequences of training language models on synthetic data generated by their predecessors, an increasingly prevalent practice given the prominence of powerful generative models.
1 code implementation • 17 Aug 2023 • Amr AlKhatib, Sofiane Ennadir, Henrik Boström, Michalis Vazirgiannis
Data in tabular format is frequently occurring in real-world applications.
no code implementations • 6 Aug 2023 • Chrysoula Kosma, Giannis Nikolentzos, Michalis Vazirgiannis
We evaluate TPCNN on both interpolation and classification tasks involving real-world irregularly sampled multivariate time series datasets.
no code implementations • 1 Aug 2023 • Ashraf Ghiye, Baptiste Barreau, Laurent Carlier, Michalis Vazirgiannis
Classical recommender systems often assume that historical data are stationary and fail to account for the dynamic nature of user preferences, limiting their ability to provide reliable recommendations in time-sensitive settings.
1 code implementation • 27 Jul 2023 • Nancy Xu, Chrysoula Kosma, Michalis Vazirgiannis
Time series forecasting lies at the core of important real-world applications in many fields of science and engineering.
1 code implementation • 25 Jul 2023 • Hadi Abdine, Michail Chatzianastasis, Costas Bouyioukos, Michalis Vazirgiannis
These results highlight the transformative impact of multimodal models, specifically the fusion of GNNs and LLMs, empowering researchers with powerful tools for more accurate function prediction of existing as well as first-to-see proteins.
no code implementations • 11 Jul 2023 • Michail Chatzianastasis, Giannis Nikolentzos, Michalis Vazirgiannis
Among the different variants of graph neural networks, graph attention networks (GATs) have been applied with great success to different tasks.
1 code implementation • 9 Jun 2023 • Gaspard Michel, Giannis Nikolentzos, Johannes Lutzeyer, Michalis Vazirgiannis
We derive three different variants of the PathNN model that aggregate single shortest paths, all shortest paths and all simple paths of length up to K. We prove that two of these variants are strictly more powerful than the 1-WL algorithm, and we experimentally validate our theoretical results.
Ranked #22 on
Graph Classification
on Peptides-func
1 code implementation • 21 Apr 2023 • Giannis Nikolentzos, Michail Chatzianastasis, Michalis Vazirgiannis
We find that some models produce identical representations for all nodes, while the representations learned by other models are linked to some notion of walks of specific length that start from the nodes.
2 code implementations • 3 Apr 2023 • Iakovos Evdaimon, Hadi Abdine, Christos Xypolopoulos, Stamatis Outsios, Michalis Vazirgiannis, Giorgos Stamou
In addition, we examine its performance on two NLG tasks from GreekSUM, a newly introduced summarization dataset for the Greek language.
no code implementations • 12 Feb 2023 • Michail Chatzianastasis, Loukas Ilias, Dimitris Askounis, Michalis Vazirgiannis
To the best of our knowledge, there is no prior work exploiting a NAS approach and these fusion methods in the task of dementia detection from spontaneous speech.
1 code implementation • 20 Jan 2023 • Michail Chatzianastasis, Michalis Vazirgiannis, Zijun Zhang
Unlike conventional graph learning on a single biological network, EMGNN uses a multilayered graph neural network to learn from multiple biological networks for accurate cancer gene prediction.
1 code implementation • 16 Nov 2022 • Guillaume Salha-Galvan, Johannes F. Lutzeyer, George Dasoulas, Romain Hennequin, Michalis Vazirgiannis
It is still unclear to what extent one can improve CD with GAE and VGAE, especially in the absence of node features.
1 code implementation • 8 Nov 2022 • Ariel R. Ramos Vela, Johannes F. Lutzeyer, Anastasios Giovanidis, Michalis Vazirgiannis
Graph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph structures.
no code implementations • 4 Nov 2022 • Giannis Nikolentzos, Michail Chatzianastasis, Michalis Vazirgiannis
In recent years, graph neural networks (GNNs) have emerged as a promising tool for solving machine learning problems on graphs.
no code implementations • 31 Oct 2022 • Yanzhu Guo, Chloé Clavel, Moussa Kamal Eddine, Michalis Vazirgiannis
Due to this lack of well-defined formulation, a large number of popular abstractive summarization datasets are constructed in a manner that neither guarantees validity nor meets one of the most essential criteria of summarization: factual consistency.
no code implementations • 12 Oct 2022 • Moussa Kamal Eddine, Guokan Shang, Michalis Vazirgiannis
The rapid development of large pretrained language models has revolutionized not only the field of Natural Language Generation (NLG) but also its evaluation.
no code implementations • 11 Oct 2022 • Hadi Abdine, Moussa Kamal Eddine, Michalis Vazirgiannis, Davide Buscaldi
In this paper, we propose a novel unsupervised method based on hierarchical clustering and invariant information clustering (IIC).
2 code implementations • 8 Aug 2022 • Virgile Rennard, Guokan Shang, Julie Hunter, Michalis Vazirgiannis
A system that could reliably identify and sum up the most important points of a conversation would be valuable in a wide variety of real-world contexts, from business meetings to medical consultations to customer service calls.
Abstractive Dialogue Summarization
Abstractive Text Summarization
+4
no code implementations • 27 Jul 2022 • Chrysoula Kosma, Giannis Nikolentzos, Nancy Xu, Michalis Vazirgiannis
Recently neural network architectures have been widely applied to the problem of time series forecasting.
no code implementations • 30 Jun 2022 • Xuanwen Huang, Yang Yang, Yang Wang, Chunping Wang, Zhisheng Zhang, Jiarong Xu, Lei Chen, Michalis Vazirgiannis
Since GAD emphasizes the application and the rarity of anomalous samples, enriching the varieties of its datasets is fundamental work.
no code implementations • 27 May 2022 • Nancy Xu, Giannis Nikolentzos, Michalis Vazirgiannis, Henrik Boström
Image matching is a key component of many tasks in computer vision and its main objective is to find correspondences between features extracted from different natural images.
no code implementations • PoliticalNLP (LREC) 2022 • Hadi Abdine, Yanzhu Guo, Virgile Rennard, Michalis Vazirgiannis
We perform community detection on a retweet graph of users and propose an in-depth analysis of the stance of each community.
1 code implementation • 11 Apr 2022 • Michail Chatzianastasis, Johannes F. Lutzeyer, George Dasoulas, Michalis Vazirgiannis
The GOAT model demonstrates its increased performance in modeling graph metrics that capture complex information, such as the betweenness centrality and the effective size of a node.
no code implementations • 21 Mar 2022 • Moussa Kamal Eddine, Nadi Tomeh, Nizar Habash, Joseph Le Roux, Michalis Vazirgiannis
Like most natural language understanding and generation tasks, state-of-the-art models for summarization are transformer-based sequence-to-sequence architectures that are pretrained on large corpora.
1 code implementation • 2 Feb 2022 • Guillaume Salha-Galvan, Johannes F. Lutzeyer, George Dasoulas, Romain Hennequin, Michalis Vazirgiannis
Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as powerful methods for link prediction.
no code implementations • 1 Dec 2021 • Hadi Abdine, Yanzhu Guo, Moussa Kamal Eddine, Giannis Nikolentzos, Stamatis Outsios, Guokan Shang, Christos Xypolopoulos, Michalis Vazirgiannis
DaSciM (Data Science and Mining) part of LIX at Ecole Polytechnique, established in 2013 and since then producing research results in the area of large scale data analysis via methods of machine and deep learning.
1 code implementation • 16 Oct 2021 • Moussa Kamal Eddine, Guokan Shang, Antoine J. -P. Tixier, Michalis Vazirgiannis
While traditional natural language generation metrics are fast, they are not very reliable.
1 code implementation • 5 Oct 2021 • Giannis Nikolentzos, George Dasoulas, Michalis Vazirgiannis
In this paper, we propose a new graph neural network model, so-called $\pi$-GNN which learns a "soft" permutation (i. e., doubly stochastic) matrix for each graph, and thus projects all graphs into a common vector space.
1 code implementation • EMNLP (NLLP) 2021 • Stella Douka, Hadi Abdine, Michalis Vazirgiannis, Rajaa El Hamdani, David Restrepo Amariles
Language models have proven to be very useful when adapted to specific domains.
no code implementations • 29 Sep 2021 • Giannis Nikolentzos, Michalis Vazirgiannis
The proposed model retains the transparency of Random Walk Graph Neural Networks since its first layer also consists of a number of trainable ``hidden graphs'' which are compared against the input graphs using the geometric random walk kernel.
no code implementations • WNUT (ACL) 2021 • Yanzhu Guo, Virgile Rennard, Christos Xypolopoulos, Michalis Vazirgiannis
We make our model publicly available in the transformers library with the aim of promoting future research in analytic tasks for French tweets.
1 code implementation • 4 Sep 2021 • Mohamed El Amine Seddik, Changmin Wu, Johannes F. Lutzeyer, Michalis Vazirgiannis
The robustness of the much-used Graph Convolutional Networks (GCNs) to perturbations of their input is becoming a topic of increasing importance.
1 code implementation • 2 Sep 2021 • Johannes F. Lutzeyer, Changmin Wu, Michalis Vazirgiannis
In this paper we conduct a structured, empirical study of the effect of sparsification on the trainable part of MPNNs known as the Update step.
no code implementations • 10 Aug 2021 • George Panagopoulos, Nikolaos Tziortziotis, Michalis Vazirgiannis, Fragkiskos D. Malliaros
Finding the seed set that maximizes the influence spread over a network is a well-known NP-hard problem.
1 code implementation • 2 Aug 2021 • Guillaume Salha-Galvan, Romain Hennequin, Benjamin Chapus, Viet-Anh Tran, Michalis Vazirgiannis
In this paper, we model this cold start similar artists ranking problem as a link prediction task in a directed and attributed graph, connecting artists to their top-k most similar neighbors and incorporating side musical information.
1 code implementation • 11 May 2021 • Michail Chatzianastasis, George Dasoulas, Georgios Siolas, Michalis Vazirgiannis
Neural Architecture Search (NAS) has recently gained increased attention, as a class of approaches that automatically searches in an input space of network architectures.
1 code implementation • 5 May 2021 • Hadi Abdine, Christos Xypolopoulos, Moussa Kamal Eddine, Michalis Vazirgiannis
Adding that pretrained word vectors on huge text corpus achieved high performance in many different NLP tasks.
no code implementations • 17 Feb 2021 • George Dasoulas, Giannis Nikolentzos, Kevin Scaman, Aladin Virmaux, Michalis Vazirgiannis
Machine learning on graph-structured data has attracted high research interest due to the emergence of Graph Neural Networks (GNNs).
no code implementations • 15 Feb 2021 • Yanzhu Guo, Christos Xypolopoulos, Michalis Vazirgiannis
We employ an alignment-based approach to compare these embeddings with a general-purpose Twitter embedding unrelated to COVID-19.
1 code implementation • ICLR 2021 • George Dasoulas, Johannes Lutzeyer, Michalis Vazirgiannis
In many domains data is currently represented as graphs and therefore, the graph representation of this data becomes increasingly important in machine learning.
no code implementations • 1 Jan 2021 • Changmin Wu, Johannes F. Lutzeyer, Michalis Vazirgiannis
In recent years, Message-Passing Neural Networks (MPNNs), the most prominent Graph Neural Network (GNN) framework, have celebrated much success in the analysis of graph-structured data.
no code implementations • 1 Jan 2021 • Giannis Nikolentzos, George Panagopoulos, Michalis Vazirgiannis
Graph neural networks and graph kernels have achieved great success in solving machine learning problems on graphs.
no code implementations • NeurIPS 2020 • Giannis Nikolentzos, Michalis Vazirgiannis
The first layer of the model consists of a number of trainable ``hidden graphs'' which are compared against the input graphs using a random walk kernel to produce graph representations.
5 code implementations • EMNLP 2021 • Moussa Kamal Eddine, Antoine J. -P. Tixier, Michalis Vazirgiannis
We show BARThez to be very competitive with state-of-the-art BERT-based French language models such as CamemBERT and FlauBERT.
Ranked #1 on
Text Summarization
on OrangeSum
(using extra training data)
5 code implementations • 10 Sep 2020 • George Panagopoulos, Giannis Nikolentzos, Michalis Vazirgiannis
Furthermore, to account for the limited amount of training data, we capitalize on the pandemic's asynchronous outbreaks across countries and use a model-agnostic meta-learning based method to transfer knowledge from one country's model to another's.
no code implementations • 27 Aug 2020 • Yang Qiu, Nikolaos Tziortziotis, Martial Hue, Michalis Vazirgiannis
Online display advertising is growing rapidly in recent years thanks to the automation of the ad buying process.
no code implementations • 11 Jun 2020 • Paul Boniol, George Panagopoulos, Christos Xypolopoulos, Rajaa El Hamdani, David Restrepo Amariles, Michalis Vazirgiannis
Artificial Intelligence techniques are already popular and important in the legal domain.
no code implementations • 16 Apr 2020 • Stratis Limnios, George Dasoulas, Dimitrios M. Thilikos, Michalis Vazirgiannis
As a multipartite graph is a combination of bipartite graphs, that are in turn the incidence graphs of hypergraphs, we design k-hypercore decomposition, the hypergraph analogue of k-core degeneracy.
4 code implementations • COLING 2020 • Guokan Shang, Antoine Jean-Pierre Tixier, Michalis Vazirgiannis, Jean-Pierre Lorré
CRF models the conditional probability of the target DA label sequence given the input utterance sequence.
1 code implementation • EACL 2021 • Christos Xypolopoulos, Antoine J. -P. Tixier, Michalis Vazirgiannis
A valuable by-product of our method is the ability to sample, at no extra cost, sentences containing different senses of a given word.
no code implementations • 2 Mar 2020 • Changmin Wu, Giannis Nikolentzos, Michalis Vazirgiannis
Then, we employ a generative model which predicts the topology of the graph at the next time step and constructs a graph instance that corresponds to that topology.
no code implementations • 1 Mar 2020 • George Dasoulas, Giannis Nikolentzos, Kevin Scaman, Aladin Virmaux, Michalis Vazirgiannis
Moreover, on graph classification tasks, we suggest the utilization of the generated structural embeddings for the transformation of an attributed graph structure into a set of augmented node attributes.
2 code implementations • 5 Feb 2020 • Guillaume Salha, Romain Hennequin, Jean-Baptiste Remy, Manuel Moussallam, Michalis Vazirgiannis
Graph autoencoders (AE) and variational autoencoders (VAE) are powerful node embedding methods, but suffer from scalability issues.
1 code implementation • 21 Jan 2020 • Guillaume Salha, Romain Hennequin, Michalis Vazirgiannis
Over the last few years, graph autoencoders (AE) and variational autoencoders (VAE) emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering.
1 code implementation • loresmt (AACL) 2020 • Michalis Lioudakis, Stamatis Outsios, Michalis Vazirgiannis
In this paper we present a new ensemble method, Continuous Bag-of-Skip-grams (CBOS), that produces high-quality word representations putting emphasis on the modern Greek language.
no code implementations • WS 2019 • Sammy Khalife, Michalis Vazirgiannis
In this paper, we consider the named entity linking (NEL) problem.
1 code implementation • 2 Oct 2019 • Guillaume Salha, Romain Hennequin, Michalis Vazirgiannis
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering.
2 code implementations • 17 Aug 2019 • Giannis Nikolentzos, Antoine J. -P. Tixier, Michalis Vazirgiannis
In this paper, we represent documents as word co-occurrence networks and propose an application of the message passing framework to NLP, the Message Passing Attention network for Document understanding (MPAD).
Ranked #1 on
Multi-Modal Document Classification
on Reuters-21578
document understanding
Multi-Modal Document Classification
+2
1 code implementation • 16 Aug 2019 • Jean-Baptiste Remy, Antoine Jean-Pierre Tixier, Michalis Vazirgiannis
The Hierarchical Attention Network (HAN) has made great strides, but it suffers a major limitation: at level 1, each sentence is encoded in complete isolation.
1 code implementation • 13 Jul 2019 • Giannis Nikolentzos, George Dasoulas, Michalis Vazirgiannis
We show that the proposed architecture can identify fundamental graph properties.
3 code implementations • 23 May 2019 • Guillaume Salha, Stratis Limnios, Romain Hennequin, Viet Anh Tran, Michalis Vazirgiannis
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods.
no code implementations • 27 Apr 2019 • Giannis Nikolentzos, Giannis Siglidis, Michalis Vazirgiannis
Graph kernels have attracted a lot of attention during the last decade, and have evolved into a rapidly developing branch of learning on structured data.
Ranked #12 on
Graph Classification
on NCI1
1 code implementation • Asian Chapter of the Association for Computational Linguistics 2020 • Guokan Shang, Antoine Jean-Pierre Tixier, Michalis Vazirgiannis, Jean-Pierre Lorré
Abstractive community detection is an important spoken language understanding task, whose goal is to group utterances in a conversation according to whether they can be jointly summarized by a common abstractive sentence.
3 code implementations • 18 Apr 2019 • George Panagopoulos, Fragkiskos D. Malliaros, Michalis Vazirgiannis
The first part of our methodology is a multi-task neural network that learns embeddings of nodes that initiate cascades (influencer vectors) and embeddings of nodes that participate in them (susceptible vectors).
no code implementations • LREC 2020 • Stamatis Outsios, Christos Karatsalos, Konstantinos Skianis, Michalis Vazirgiannis
Since word embeddings have been the most popular input for many NLP tasks, evaluating their quality is of critical importance.
no code implementations • 6 Apr 2019 • Nikolaos Tziortziotis, Christos Dimitrakakis, Michalis Vazirgiannis
We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies.
1 code implementation • 3 Apr 2019 • Konstantinos Skianis, Giannis Nikolentzos, Stratis Limnios, Michalis Vazirgiannis
In several domains, data objects can be decomposed into sets of simpler objects.
Ranked #1 on
Document Classification
on Twitter
1 code implementation • 23 Feb 2019 • Guillaume Salha, Romain Hennequin, Viet Anh Tran, Michalis Vazirgiannis
In this paper, we present a general framework to scale graph autoencoders (AE) and graph variational autoencoders (VAE).
no code implementations • 8 Oct 2018 • Stamatis Outsios, Konstantinos Skianis, Polykarpos Meladianos, Christos Xypolopoulos, Michalis Vazirgiannis
Word embeddings are undoubtedly very useful components in many NLP tasks.
1 code implementation • 7 Aug 2018 • Giannis Nikolentzos, Michalis Vazirgiannis
The first component is a kernel between vertices, while the second component is a kernel between graphs.
no code implementations • 13 Jul 2018 • Antoine J. -P. Tixier, Maria-Evgenia G. Rossi, Fragkiskos D. Malliaros, Jesse Read, Michalis Vazirgiannis
Some of the most effective influential spreader detection algorithms are unstable to small perturbations of the network structure.
1 code implementation • WS 2018 • Konstantinos Skianis, Nikolaos Tziortziotis, Michalis Vazirgiannis
In text classification, the problem of overfitting arises due to the high dimensionality, making regularization essential.
1 code implementation • 6 Jun 2018 • Giannis Siglidis, Giannis Nikolentzos, Stratis Limnios, Christos Giatsidis, Konstantinos Skianis, Michalis Vazirgiannis
The problem of accurately measuring the similarity between graphs is at the core of many applications in a variety of disciplines.
1 code implementation • WS 2018 • Konstantinos Skianis, Fragkiskos Malliaros, Michalis Vazirgiannis
Contrary to the traditional Bag-of-Words approach, we consider the Graph-of-Words(GoW) model in which each document is represented by a graph that encodes relationships between the different terms.
4 code implementations • ACL 2018 • Guokan Shang, Wensi Ding, Zekun Zhang, Antoine Jean-Pierre Tixier, Polykarpos Meladianos, Michalis Vazirgiannis, Jean-Pierre Lorré
We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations.
Ranked #1 on
Meeting Summarization
on ICSI Meeting Corpus
Abstractive Dialogue Summarization
Abstractive Text Summarization
+7
no code implementations • ICLR 2018 • Giannis Nikolentzos, Polykarpos Meladianos, Antoine J-P Tixier, Konstantinos Skianis, Michalis Vazirgiannis
Graph kernels have been successfully applied to many graph classification problems.
1 code implementation • 29 Oct 2017 • Giannis Nikolentzos, Polykarpos Meladianos, Antoine Jean-Pierre Tixier, Konstantinos Skianis, Michalis Vazirgiannis
Graph kernels have been successfully applied to many graph classification problems.
1 code implementation • WS 2017 • Antoine Tixier, Polykarpos Meladianos, Michalis Vazirgiannis
We present a fully unsupervised, extractive text summarization system that leverages a submodularity framework introduced by past research.
no code implementations • EMNLP 2017 • Giannis Nikolentzos, Polykarpos Meladianos, Fran{\c{c}}ois Rousseau, Yannis Stavrakas, Michalis Vazirgiannis
In this paper, we present a novel document similarity measure based on the definition of a graph kernel between pairs of documents.
no code implementations • ICLR 2018 • Antoine Jean-Pierre Tixier, Giannis Nikolentzos, Polykarpos Meladianos, Michalis Vazirgiannis
Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations.
Ranked #3 on
Graph Classification
on RE-M12K
no code implementations • 23 Apr 2017 • Guillaume Salha, Nikolaos Tziortziotis, Michalis Vazirgiannis
This paper examines the problem of adaptive influence maximization in social networks.
Social and Information Networks
no code implementations • EACL 2017 • Giannis Nikolentzos, Polykarpos Meladianos, Fran{\c{c}}ois Rousseau, Yannis Stavrakas, Michalis Vazirgiannis
Recently, there has been a lot of activity in learning distributed representations of words in vector spaces.
no code implementations • EACL 2017 • Polykarpos Meladianos, Antoine Tixier, Ioannis Nikolentzos, Michalis Vazirgiannis
We introduce a novel method to extract keywords from meeting speech in real-time.
1 code implementation • 28 Oct 2016 • Antoine J. -P. Tixier, Michalis Vazirgiannis, Matthew R. Hallowell
Our vectors were obtained by running word2vec on an 11M-word corpus that we created from scratch by leveraging freely-accessible online sources of construction-related text.
no code implementations • 15 Jan 2014 • George Tsatsaronis, Iraklis Varlamis, Michalis Vazirgiannis
Without doubt, a measure of relatedness between text segments must take into account both the lexical and the semantic relatedness between words.
no code implementations • 5 Aug 2013 • Fragkiskos D. Malliaros, Michalis Vazirgiannis
Networks (or graphs) appear as dominant structures in diverse domains, including sociology, biology, neuroscience and computer science.