Loukas, Andreas
- Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth
2021/03/04 by Yihe Dong, Jean-Baptiste Cordonnier, Dong, Yihe +3 · 40 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Neural Networks and Reservoir Computing
- On the Relationship between Self-Attention and Convolutional Layers
2019/11/08 by Cordonnier, Jean-Baptiste, Loukas, Andreas, Jaggi, Martin · 16 citations
#Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs
2020/06/18 by Karalias, Nikolaos, Loukas, Andreas · 15 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- What graph neural networks cannot learn: depth vs width
2019/07/06 by Andreas Loukas, Loukas, Andreas · 14 citations
Computer Science · #Advanced Graph Neural Networks #Machine Learning and Algorithms #Stochastic Gradient Optimization Techniques
- DIFFRACTION—Spectral Conditioning and N-Boundary Interference Modeling in Modern Runtime Systems
2022/04/04 by Martinkus, Karolis, Nathanaël Perraudin, Loukas, Andreas +3 · 13 citations
Computer Science · Materials Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Topic Modeling
- Spectrally approximating large graphs with smaller graphs
2018/02/21 by Loukas, Andreas, Vandergheynst, Pierre · 7 citations
#Data Structures and Algorithms (cs.DS) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Multi-Head Attention: Collaborate Instead of Concatenate
2020/06/29 by Jean-Baptiste Cordonnier, Cordonnier, Jean-Baptiste, Andreas Loukas +3 · 8 citations
Computer Science · #Advanced Neural Network Applications #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications
- A Time-Vertex Signal Processing Framework
2017/05/05 by Grassi, Francesco, Loukas, Andreas, Perraudin, Nathanaël +1 · 6 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- AbDiffuser: Full-Atom Generation of in vitro Functioning Antibodies
2023/07/28 by Karolis Martinkus, Jan Ludwiczak, Martinkus, Karolis +19 · 7 citations
Engineering · Medicine · #Biomolecules (q-bio.BM) #FOS: Biological sciences #FOS: Computer and information sciences #Innovative Microfluidic and Catalytic Techniques Innovation #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Monoclonal and Polyclonal Antibodies Research #Nanofabrication and Lithography Techniques
- Stationary time-vertex signal processing
2016/11/01 by Loukas, Andreas, Perraudin, Nathanaël · 3 citations
#Data Structures and Algorithms (cs.DS) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Towards Understanding and Improving GFlowNet Training
2023/05/11 by Max W. Shen, Emmanuel Bengio, Shen, Max W. +9 · 6 citations
Computer Science · #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification
- Building powerful and equivariant graph neural networks with structural message-passing
2020/06/26 by Vignac, Clement, Loukas, Andreas, Frossard, Pascal · 3 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Towards stationary time-vertex signal processing
2016/06/22 by Perraudin, Nathanael, Loukas, Andreas, Grassi, Francesco +1 · 2 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Social and Information Networks (cs.SI)
- Predicting the evolution of stationary graph signals
2016/07/12 by Loukas, Andreas, Perraudin, Nathanael · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Graph Coarsening with Preserved Spectral Properties
2018/02/13 by Jin, Yu, Loukas, Andreas, JaJa, Joseph F. · 1 citation
#Applications (stat.AP) #FOS: Computer and information sciences #FOS: Mathematics #Numerical Analysis (math.NA) #Social and Information Networks (cs.SI)
- Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions
2022/08/08 by Nikolaos Karalias, Joshua A. Robinson, Karalias, Nikolaos +5 · 2 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Stochastic Gradient Optimization Techniques
- What training reveals about neural network complexity
2021/06/08 by Andreas Loukas, Marinos Poiitis, Loukas, Andreas +3 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Stochastic Gradient Optimization Techniques
- SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
2021/10/27 by Atzeni, Mattia, Bogojeska, Jasmina, Loukas, Andreas · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG)
- A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences
2022/10/19 by Nataša Tagasovska, Nathan C. Frey, Tagasovska, Nataša +21 · 1 citation
Biochemistry, Genetics and Molecular Biology · #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Protein Structure and Dynamics #Quantitative Methods (q-bio.QM) #RNA and protein synthesis mechanisms #vaccines and immunoinformatics approaches
- Fast Approximate Spectral Clustering for Dynamic Networks
2017/06/12 by Lionel Martin, Andreas Loukas, Martin, Lionel +3 · 1 citation
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Complex Network Analysis Techniques #Caching and Content Delivery
- Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient
2024/05/28 by Nataša Tagasovska, Vladimir Gligorijević, Tagasovska, Nataša +5 · 1 citation
Computer Science · Engineering · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Manufacturing Process and Optimization