Filters








22 Hits in 1.0 sec

Bayesian Deep Learning for Graphs [article]

Federico Errica
<span title="2022-02-24">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The adaptive processing of structured data is a long-standing research topic in machine learning that investigates how to automatically learn a mapping from a structured input to outputs of various nature. Recently, there has been an increasing interest in the adaptive processing of graphs, which led to the development of different neural network-based methodologies. In this thesis, we take a different route and develop a Bayesian Deep Learning framework for graph learning. The dissertation
more &raquo; ... ns with a review of the principles over which most of the methods in the field are built, followed by a study on graph classification reproducibility issues. We then proceed to bridge the basic ideas of deep learning for graphs with the Bayesian world, by building our deep architectures in an incremental fashion. This framework allows us to consider graphs with discrete and continuous edge features, producing unsupervised embeddings rich enough to reach the state of the art on several classification tasks. Our approach is also amenable to a Bayesian nonparametric extension that automatizes the choice of almost all model's hyper-parameters. Two real-world applications demonstrate the efficacy of deep learning for graphs. The first concerns the prediction of information-theoretic quantities for molecular simulations with supervised neural models. After that, we exploit our Bayesian models to solve a malware-classification task while being robust to intra-procedural code obfuscation techniques. We conclude the dissertation with an attempt to blend the best of the neural and Bayesian worlds together. The resulting hybrid model is able to predict multimodal distributions conditioned on input graphs, with the consequent ability to model stochasticity and uncertainty better than most works. Overall, we aim to provide a Bayesian perspective into the articulated research field of deep learning for graphs.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.12348v1">arXiv:2202.12348v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ayrl5zr6q5dfjhqspecg4umsxm">fatcat:ayrl5zr6q5dfjhqspecg4umsxm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220530055751/https://arxiv.org/pdf/2202.12348v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/91/8a/918a2fa3197655ad9870b3cafeebc22ca971cfbb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.12348v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Theoretically Expressive and Edge-aware Graph Learning [article]

Federico Errica, Davide Bacciu, Alessio Micheli
<span title="2020-01-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a new Graph Neural Network that combines recent advancements in the field. We give theoretical contributions by proving that the model is strictly more general than the Graph Isomorphism Network and the Gated Graph Neural Network, as it can approximate the same functions and deal with arbitrary edge values. Then, we show how a single node information can flow through the graph unchanged.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.09005v1">arXiv:2001.09005v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4rc4rjkyjbb4heshczkkfbcr6i">fatcat:4rc4rjkyjbb4heshczkkfbcr6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321080048/https://arxiv.org/pdf/2001.09005v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.09005v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Concept Matching for Low-Resource Classification [article]

Federico Errica, Ludovic Denoyer, Bora Edizel, Fabio Petroni, Vassilis Plachouras, Fabrizio Silvestri, Sebastian Riedel
<span title="2020-06-01">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Correspondence to: Federico Errica <federico.errica@phd.unipi.it>. https://github.com/facebookresearch/parcus.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00937v1">arXiv:2006.00937v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4skhmd4ixbe6hmmls54mxvpltm">fatcat:4skhmd4ixbe6hmmls54mxvpltm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200927143719/https://arxiv.org/pdf/2006.00937v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b1/57/b157d8e05e03869cd743d592a90d082687817ecc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00937v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Graph Mixture Density Networks [article]

Federico Errica, Davide Bacciu, Alessio Micheli
<span title="2021-06-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Correspondence to: Federico Errica <federico.errica@phd.unipi.it>, Davide Bacciu <bacciu@di.unipi.it>, Alessio Micheli <micheli@di.unipi.it>.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.03085v3">arXiv:2012.03085v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bukkvx7z7fgobm32rqdz2t2com">fatcat:bukkvx7z7fgobm32rqdz2t2com</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210630065320/https://arxiv.org/pdf/2012.03085v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/11/25/1125460df9aa0107ebf8f07ab2d4eb3c56729198.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.03085v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification [article]

Antonio Carta, Andrea Cossu, Federico Errica, Davide Bacciu
<span title="2021-03-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential data have a tangible impact on performances when applied to graph data. To do so, we experiment with a structure-agnostic model and a deep graph network in a robust and controlled environment on three different datasets. The benchmark is complemented by an
more &raquo; ... stigation on the effect of structure-preserving regularization techniques on catastrophic forgetting. We find that replay is the most effective strategy in so far, which also benefits the most from the use of regularization. Our findings suggest interesting future research at the intersection of the continual and graph representation learning fields. Finally, we provide researchers with a flexible software framework to reproduce our results and carry out further experiments.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.11750v1">arXiv:2103.11750v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rgzetw7advf53oitqtpgdwquhm">fatcat:rgzetw7advf53oitqtpgdwquhm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210325021627/https://arxiv.org/pdf/2103.11750v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f1/f8/f1f850428cae5cd5c535068c3f1b940915fbfe79.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.11750v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Gentle Introduction to Deep Learning for Graphs [article]

Davide Bacciu, Federico Errica, Alessio Micheli, Marco Podda
<span title="2019-12-29">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is designed as a tutorial introduction to the field of deep learning for graphs. It favours a consistent and progressive introduction of the main concepts and
more &raquo; ... rchitectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view to the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. It introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. The methodological exposition is complemented by a discussion of interesting research challenges and applications in the field.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.12693v1">arXiv:1912.12693v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lww6akhmuvbe5hu335hl7ggghu">fatcat:lww6akhmuvbe5hu335hl7ggghu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321051454/https://arxiv.org/pdf/1912.12693v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.12693v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Accelerating the identification of informative reduced representations of proteins with deep learning for graphs [article]

Federico Errica, Marco Giulini, Davide Bacciu, Roberto Menichetti, Alessio Micheli, Raffaello Potestio
<span title="2020-07-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The limits of molecular dynamics (MD) simulations of macromolecules are steadily pushed forward by the relentless developments of computer architectures and algorithms. This explosion in the number and extent (in size and time) of MD trajectories induces the need of automated and transferable methods to rationalise the raw data and make quantitative sense out of them. Recently, an algorithmic approach was developed by some of us to identify the subset of a protein's atoms, or mapping, that
more &raquo; ... es the most informative description of it. This method relies on the computation, for a given reduced representation, of the associated mapping entropy, that is, a measure of the information loss due to the simplification. Albeit relatively straightforward, this calculation can be time consuming. Here, we describe the implementation of a deep learning approach aimed at accelerating the calculation of the mapping entropy. The method relies on deep graph networks, which provide extreme flexibility in the input format. We show that deep graph networks are accurate and remarkably efficient, with a speedup factor as large as 10^5 with respect to the algorithmic computation of the mapping entropy. Applications of this method, which entails a great potential in the study of biomolecules when used to reconstruct its mapping entropy landscape, reach much farther than this, being the scheme easily transferable to the computation of arbitrary functions of a molecule's structure.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08658v1">arXiv:2007.08658v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3a6faqwb2vf3lb3mjcigvg3abe">fatcat:3a6faqwb2vf3lb3mjcigvg3abe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200723223326/https://arxiv.org/pdf/2007.08658v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9b/54/9b54a23b1aa8afcff222b5e3b965a3c267608b28.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08658v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing [article]

Davide Bacciu, Federico Errica, Alessio Micheli
<span title="2019-11-25">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce the Contextual Graph Markov Model, an approach combining ideas from generative models and neural networks for the processing of graph data. It founds on a constructive methodology to build a deep architecture comprising layers of probabilistic models that learn to encode the structured information in an incremental fashion. Context is diffused in an efficient and scalable way across the graph vertexes and edges. The resulting graph encoding is used in combination with
more &raquo; ... models to address structure classification benchmarks.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.10636v2">arXiv:1805.10636v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/daludka3qzaxbbnrkzgqcwnlui">fatcat:daludka3qzaxbbnrkzgqcwnlui</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200914101531/https://arxiv.org/pdf/1805.10636v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ca/d0/cad0c6e992a9019e459fbb9effab4dedd209c9e7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.10636v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Fair Comparison of Graph Neural Networks for Graph Classification [article]

Federico Errica, Marco Podda, Davide Bacciu, Alessio Micheli
<span title="2022-02-17">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Experimental reproducibility and replicability are critical topics in machine learning. Authors have often raised concerns about their lack in scientific publications to improve the quality of the field. Recently, the graph representation learning field has attracted the attention of a wide research community, which resulted in a large stream of works. As such, several Graph Neural Network models have been developed to effectively tackle graph classification. However, experimental procedures
more &raquo; ... en lack rigorousness and are hardly reproducible. Motivated by this, we provide an overview of common practices that should be avoided to fairly compare with the state of the art. To counter this troubling trend, we ran more than 47000 experiments in a controlled and uniform framework to re-evaluate five popular models across nine common benchmarks. Moreover, by comparing GNNs with structure-agnostic baselines we provide convincing evidence that, on some datasets, structural information has not been exploited yet. We believe that this work can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.09893v3">arXiv:1912.09893v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h4ngcck57nc3dj6yor646vgz7q">fatcat:h4ngcck57nc3dj6yor646vgz7q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220523205134/https://arxiv.org/pdf/1912.09893v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3d/b5/3db5fcb595492dcd64663c00d56f004dfafa689c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.09893v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Deep Graph Network–Enhanced Sampling Approach to Efficiently Explore the Space of Reduced Representations of Proteins

Federico Errica, Marco Giulini, Davide Bacciu, Roberto Menichetti, Alessio Micheli, Raffaello Potestio
<span title="2021-04-29">2021</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/zqzewb742bdglfxhkef3ke6cla" style="color: black;">Frontiers in Molecular Biosciences</a> </i> &nbsp;
Copyright © 2021 Errica, Giulini, Bacciu, Menichetti, Micheli and Potestio. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fmolb.2021.637396">doi:10.3389/fmolb.2021.637396</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33996896">pmid:33996896</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8116519/">pmcid:PMC8116519</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dxxk5ajtazdxbecccgijskkcvm">fatcat:dxxk5ajtazdxbecccgijskkcvm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210430045611/https://fjfsdata01prod.blob.core.windows.net/articles/files/637396/pubmed-zip/.versions/1/.package-entries/fmolb-08-637396.pdf?sv=2018-03-28&amp;sr=b&amp;sig=TK72HjPNrigWRaWKr2Qq38K%2BcmOsEdEMvkJgIPJkHDM%3D&amp;se=2021-04-30T04%3A56%3A41Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fmolb-08-637396.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fd/b5/fdb59a4ddf81048aee110f45ddb9c40497f12568.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fmolb.2021.637396"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8116519" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

FA3L at SemEval-2017 Task 3: A ThRee Embeddings Recurrent Neural Network for Question Answering

Giuseppe Attardi, Antonio Carta, Federico Errica, Andrea Madotto, Ludovica Pannitto
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/aa3ggf3tbjarfj2zylzuxxqvdi" style="color: black;">Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)</a> </i> &nbsp;
In this paper we present ThReeNN, a model for Community Question Answering, Task 3, of SemEval-2017. The proposed model exploits both syntactic and semantic information to build a single and meaningful embedding space. Using a dependency parser in combination with word embeddings, the model creates sequences of inputs for a Recurrent Neural Network, which are then used for the ranking purposes of the Task. The score obtained on the official test data shows promising results.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/s17-2048">doi:10.18653/v1/s17-2048</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/semeval/AttardiCEMP17.html">dblp:conf/semeval/AttardiCEMP17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w7d6cd2gcbg7jitxmgni7fl52m">fatcat:w7d6cd2gcbg7jitxmgni7fl52m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305090635/https://www.aclweb.org/anthology/S17-2048.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1c/32/1c32044a1c7d0eade8780d24b709ac7b3d7384d0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/s17-2048"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Catastrophic Forgetting in Deep Graph Networks: A Graph Classification Benchmark

Antonio Carta, Andrea Cossu, Federico Errica, Davide Bacciu
<span title="2022-02-04">2022</span>
., 2018; Errica et al., 2020) .  ...  The most common baseline we find in the literature (Dwivedi et al., 2020; Errica et al., 2020 ) is a multi-layer perceptron (MLP) that is invariant to the ordering of the nodes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frai.2022.824655">doi:10.3389/frai.2022.824655</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35187476">pmid:35187476</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8855050/">pmcid:PMC8855050</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/35t7jak5qrhere77ohpnjuvheq">fatcat:35t7jak5qrhere77ohpnjuvheq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220421185334/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC8855050&amp;blobtype=pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/c3/9cc3180b6da7fabb7ed1fcace06bd31f751ab829.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frai.2022.824655"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8855050" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Complex Data: Learning Trustworthily, Automatically, and with Guarantees

Luca Oneto, Nicolò Navarin, Battista Biggio, Federico Errica, Alessio Micheli, Franco Scarselli, Monica Bianchini, Alessandro Sperduti
<span title="">2021</span> <i title="Ciaco - i6doc.com"> ESANN 2021 proceedings </i> &nbsp; <span class="release-stage">unpublished</span>
Machine Learning (ML) achievements enabled automatic extraction of actionable information from data in a wide range of decisionmaking scenarios. This demands for improving both ML technical aspects (e.g., design and automation) and human-related metrics (e.g., fairness, robustness, privacy, and explainability), with performance guarantees at both levels. The aforementioned scenario posed three main challenges: (i) Learning from Complex Data (i.e., sequence, tree, and graph data), (ii) Learning
more &raquo; ... rustworthily, and (iii) Learning Automatically with Guarantees. The focus of this special session is on addressing one or more of these challenges with the final goal of Learning Trustworthily, Automatically, and with Guarantees from Complex Data.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14428/esann/2021.es2021-6">doi:10.14428/esann/2021.es2021-6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pahz7bwkqzcllnpy5ckl427kg4">fatcat:pahz7bwkqzcllnpy5ckl427kg4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211016041206/https://www.esann.org/sites/default/files/proceedings/2021/ES2021-6.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/03/98/0398a00bcb5d34a5aa7d757117e591d54a895484.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14428/esann/2021.es2021-6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Robust Malware Classification via Deep Graph Networks on Call Graph Topologies

Federico Errica, Giacomo Iadarola, Fabio Martinelli, Francesco Mercaldo, Alessio Micheli
<span title="">2021</span> <i title="Ciaco - i6doc.com"> ESANN 2021 proceedings </i> &nbsp; <span class="release-stage">unpublished</span>
We propose a malware classification system that is shown to be robust to some common intra-procedural obfuscation techniques. Indeed, by training the Contextual Graph Markov Model on the call graph representation of a program, we classify it using only topological information, which is unaffected by such obfuscations. In particular, we show that the structure of the call graph is sufficient to achieve good accuracy on a multi-class classification benchmark.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14428/esann/2021.es2021-82">doi:10.14428/esann/2021.es2021-82</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m7cwgs5p5jeanm3o7igteaeg3y">fatcat:m7cwgs5p5jeanm3o7igteaeg3y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211018164949/https://www.esann.org/sites/default/files/proceedings/2021/ES2021-82.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/02/0b/020b53632030438b9a74bf08627d297bb0239619.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14428/esann/2021.es2021-82"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

On the Bottleneck of Graph Neural Networks and its Practical Implications [article]

Uri Alon, Eran Yahav
<span title="2021-03-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
ACKNOWLEDGMENTS We would like to thank Federico Errica for his help in using his framework; Petar Veličković for helpful discussions about GAT; and Jorge Perez for helpful discussions about the expressiveness  ...  † -previously reported by Errica et al. (2020).  ...  We used the same 10-folds and split as Errica et al. (2020) . Models We used the implementation of Errica et al. (2020) who performed a fair and thorough comparison between GNNs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.05205v4">arXiv:2006.05205v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cu72ummiz5blrlzje2ubxmi2cy">fatcat:cu72ummiz5blrlzje2ubxmi2cy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210310020047/https://arxiv.org/pdf/2006.05205v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/26/c9/26c9a0c0740b47ff0d866d80cdc2f3207f955d72.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.05205v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 22 results