Italy

Recent Transformer-based architectures, e.g., BERT, provide impressive results in many Natural Language Processing tasks. However, most of the adopted benchmarks are made of (sometimes hundreds of) thousands of examples. In many real scenarios, obtaining high- quality annotated data is expensive and time consuming; in contrast, unlabeled examples characterizing the target task can be, in general, easily collected. One promising method to enable semi-supervised learning has been proposed in image processing, based on Semi- Supervised Generative Adversarial Networks. In this paper, we propose GAN-BERT that ex- tends the fine-tuning of BERT-like architectures with unlabeled data in a generative adversarial setting. Experimental results show that the requirement for annotated examples can be drastically reduced (up to only 50-100 annotated examples), still obtaining good performances in several sentence classification tasks.

AIxIA 2021

GAN-BERT: Semi-supervised Learning through Generative Adversarial Learning in Transformer-based Architectures

workshop paper

[![](https://assets.underline.io/uploads/markdown_image/1/image/9a88ae95fbde06e80f4bcf6d4f7d133a.png)](https://certificateaixia.paperform.co/)
The certificate will be provided by December 17. 
In case you need it urgently please contact: francesca.gasparini@unimib.it. 

 

The 20th International Conference of the Italian Association for Artificial Intelligence (**AIxIA 2021**) is organized by AIxIA (Associazione Italiana per l’Intelligenza Artificiale), which is a non-profit scientific society founded in 1988 and devoted to the promotion of Artificial Intelligence. The society aims to increase the public awareness of AI, encourage the teaching of it and promote research in the field.

 
 



**General Chair**

Stefania Bandini, University of Milano-Bicocca, Italyand RCAST - The University of Tokyo, Japan


**Program Chairs**

Viviana Mascardi, University of Genova, Italy; Matteo Palmonari, University of Milano-Bicocca, Italy; Giuseppe Vizzari, University of Milano-Bicocca, Italy

**Organizing Committee**

Francesca Gasparini, University of Milano-Bicocca, Italy (**Chair**); Stefano Ferilli, University of Bari, Italy; Marta Giltri, University of Milano-Bicocca, Italy; Daniela Briola, University of Insubria, Italy


**Publicity and Communication Committee**

Elisabetta Fersini, University of Milano-Bicocca, Italy (**Chair**); Angelo Ferrando, University of Genova, Italy; Francesca Alessandra Lisi, University of Bari, Italy; Giovanni Stilo, University of L'Aquila, Italy; Marco Viviani, University of Milano-Bicocca, Italy


**Workshop Chairs**

Gabriella Cortellessa, ISTC-CNR, Rome, Italy; Silvia Rossi, University of Naples Federico II, Italy; Fabio Stella, University of Milano-Bicocca, Italy


**PC Members**

Fulvio Mastrogiovanni, University of Genova, Italy; Roberto Basili, University of Rome Tor Vergata, Italy; Nicola Gatti, Polytechnic University of Milan, Italy; Stefano Bistarelli, University of Perugia, Italy; Piero Poccianti, Consorzio Operativo Gruppo MPS, Italy; Francesco Scarcello, University of Calabria, Italy; Flavio S. Correa Da Silva, University of São Paulo, Brazil; Elena Cabrio, Université Côte d'Azur, CNRS, Inria, I3S, France; Antonio Lieto, University of Turin, Italy; Diego Calvanese, Free University of Bozen-Bolzano, Italy; Alessio Micheli, University of Pisa, Italy; Francesca A. Lisi University of Bari Aldo Moro, Italy; Mauro Vallati, University of Huddersfield, United Kingdom; Bernardo Magnini, Fondazione Bruno Kessler (FBK), Italy; Luigia C. Aiello, Sapienza University of Rome, Italy; Rafael H. Bordini, Pontifical Catholic University of Rio Grande do Sul, Brazil; Chiara Ghidini, Fondazione Bruno Kessler (FBK), Italy; Federico Bergenti, University of Parma, Italy; Francesco Ricca, University of Calabria, Italy; Andrea Burattin, Technical University of Denmark, Denmark; Angelo Oddi, ISTC-CNR, Italian National Research Council, Italy; Farshad Badie, Aalborg University, Denmark; Emanuel Sallinger, University of Oxford, United Kingdom; Marin Lujak, University Rey Juan Carlos, Spain; Giancarlo Fortino, University of Calabria, Italy; Salvatore Gaglio, University of Palermo, Italy; Johannes K. Fichte, TU Dresden, Germany; Matteo Baldoni, University of Turin, Italy; Fabrizio Riguzzi, Univeristy of Ferrara, Italy; Ivana Dusparic, Trinity College Dublin, Ireland; Serena Villata, CNRS - Laboratoire d'Informatique, Signaux et Systèmes de Sophia-Antipolis, France; Paolo Rosso, Technical University of Valencia, Spain; Ana L. C. Bazzan, Federal University of Rio Grande do Sul, Brazil; Gianluigi Greco, University of Calabria, Italy; Stefano Cagnoni, University of Parma, Italy; Gian Luca Pozzato, University of Turin, Italy; Salvatore Ruggieri, University of Turin, Italy; Claudio Di Ciccio, Sapienza University of Rome, Italy; Eloisa Vargiu, Cetaqua, Water Technology Center, Spain; Marco Maratea, University of Genova, Italy; Andrea Roli, University of Bologna, Italy; Viviana Patti, University of Turin, Italy; Stefania Costantini, University of L'Aquila, Italy; Antonius Weinzierl, Vienna University of Technology, Austria; Silvia Rossi, University of Naples Federico II, Italy; Giovanni Semeraro, University of Bari, Italy; Luciano Serafini, Fondazione Bruno Kessler (FBK), Italy; Laura Giordano, University of Eastern Piedmont, Italy; Ernesto Jimenez-Ruiz, City, University of London, United Kingdom; Marco Gavanelli, University of Ferrara, Italy; Federico Chesani, University of Bologna, Italy

Please register with AIxIA to be able to enter the conference on Underline.io. If you have already registered, please login to Underline.io to be able to see full conference content. In case you do not have an Underline account, please create one. Thank you

Please login to your Underline account

The 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2021) is organized by AIxIA (Associazione Italiana per l’Intelligenza Artificiale), which is a non-profit scientific society founded in 1988 and devoted to the promotion of Artificial Intelligence. The society aims to increase the public awareness of AI, encourage the teaching of it and promote research in the field.

The increasing complexity and unpredictability of many ICT scenarios let us envision that future systems will have to dynamically learn how to act and adapt to face evolving situations with little or no a priori knowledge, both at the level of individual components and at the collective level. In other words, such systems should become able to autonomously develop models of themselves and of their environment. Autonomous development includes: learning models of own capabilities; learning how to act purposefully towards the achievement of specific goals; and learning how to act collectively, i.e., accounting for the presence of others. In this paper, we introduce the vision of autonomous development in ICT systems, by framing its key concepts and by illustrating suitable application domains. Then, we overview the many research areas that are contributing or can potentially contribute to the realization of the vision, and identify some key research challenges.

Autonomous Development:Concepts and Challenges

Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of security by causing gradient-based attacks to fail, and they have been broken under more rigorous evaluations. Although guidelines and best practices have been suggested to improve current adversarial robustness evaluations, the lack of automatic testing and debugging tools makes it difficult to apply these recommendations in a systematic manner. In this work, we overcome these limitations by (i) defining a set of quantitative indicators which unveil common failures in the optimization of gradient-based attacks, and (ii) proposing specific mitigation strategies within a systematic evaluation protocol. Our extensive experimental analysis shows that the proposed indicators of failure can be used to visualize, debug and improve current adversarial robustness evaluations, providing a first concrete step towards automatizing and systematizing current adversarial robustness evaluations. Our open-source code is available at: https://github.com/pralab/IndicatorsOfAttackFailure.

Towards Debugging and Improving Adversarial Robustness Evaluations

Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of Artificial Intelligence (AI) is building an artificial “continual learning” agent that constructs a sophisticated understanding of the world from its own experience through the autonomous incremental development of ever more complex knowledge and skills (Parisi, 2019). However, despite early speculations and few pioneering works (Ring, 1998; Thrun, 1998; Carlson, 2010), very little research and effort has been devoted to address this vision. Current AI systems greatly suffer from the exposure to new data or environments which even slightly differ from the ones for which they have been trained for (Goodfellow, 2013). Moreover, the learning process is usually constrained on fixed datasets within narrow and isolated tasks which may hardly lead to the emergence of more complex and autonomous intelligent behaviors. In essence, continual learning and adaptation capabilities, while more than often thought as fundamental pillars of every intelligent agent, have been mostly left out of the main AI research focus. In this tutorial, we propose to summarize the application of these ideas in light of the more recent advances in machine learning research and in the context of deep architectures for AI (Lomonaco, 2019). Starting from a motivation and a brief history, we link recent Continual Learning advances to previous research endeavours on related topics and we summarize the state-of-the-art in terms of major approaches, benchmarks and key results. In the second part of the tutorial we plan to cover more exploratory studies about Continual Learning with low supervised signals and the relationships with other paradigms such as Unsupervised, Semi-Supervised and Reinforcement Learning. We will also highlight the impact of recent Neuroscience discoveries in the design of original continual learning algorithms as well as their deployment in real-world applications. Finally, we will underline the notion of continual learning as a key technological enabler for Sustainable Machine Learning and its societal impact, as well as recap interesting research questions and directions worth addressing in the future.

Continual Learning with Deep Architectures

Tiny Machine Learning (TinyML) is a novel research area aiming at designing machine
and deep learning (MDL) models and algorithms able to be executed on tiny devices,
such as Internet-of-Things units, edge devices or embedded systems.
The research in this area is nowadays taking giant steps in the field of frameworks
(e.g., Tensorflow Light for Microcontrollers [2], ARM’s CMSIS-NN [5]), algorithms

(e.g., quantizations [4] and pruning mechanisms [6]), models (e.g., [7], [1] ) and learn-
ing paradigms (e.g., [3]). Advances obtained with these researches allow MDL models

to overcame the constraints on computation, memory and energy consumption char-
acterizing the technology, hence paving the way for a pervasive diffusion of TinyML

applications in everyday life (e.g., smart home and buildings, smart cars, e-health,
industry 4.0).

TinyML represents a great opportunity in designing smarter, safer and more effi-
cient pervasive applications but introduces relevant challenges from the point of view

of the privacy of users. Indeed cameras and microphones can represent crucial as-
sets for these technologies but they also bring relevant privacy concerns. From this

perspective, radar sensors are currently emerging as a valid alternative. Given the
impossibility to recognize precisely the identity of the user, they can be used in cases
where it is important to recognize the presence or the behaviour of human beings while
guaranteeing at the same time to preserve their privacy. UltrawideBand (UWB), in
particular, is a radar technology that is particularly promising for use in pervasive
systems. Indeed, its precision, low energy consumption and fastness are particularly
suitable for privacy-preserving TinyML applications.
This work will explore the advances in the field of tinyML solutions and algorithms
for privacy-preserving UWB-based pervasive applications.

Is ”privacy” the next big thing in TinyML?

Tractable languages for Statistical Relational AI

Machine Learning for Smart Tourism

Beyond English: the Case for Initiatives around Massive Models in Low(er)-resource Languages

In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neurons. We show that some specializations of NEWRON allow the network to be interpretable with no change in their expressiveness. By just inspecting the models produced by our NEWRON-based networks, we can understand the rules governing the task. Extensive experiments show that the quality of the generated models is better than traditional interpretable models and in line or better than standard neural networks.

Newron: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks

Graph Neural Networks (GNNs) are a wide class of connectionist models for graph processing. Recent studies have linked the expressive power of GNNs to the Weisfeiler– Lehman algorithm, which is a method of verifying whether two graphs are isomorphic or not. On the other hand, it was also observed that the computational power of GNNs is related to the unfolding trees, namely trees that can be constructed by visiting the graph from a given node. In this paper, we unify these two theories and prove that the Weisfeiler–Lehman test and the unfolding trees induce the same equivalence relationship on the graph nodes: such an equivalence exactly explains which nodes can or cannot be distinguished by a GNN. Moreover, it is proved that GNNs can approximate in probability, up to any precision, any function on graphs that respects the above mentioned equivalence relationship. These results provide a more comprehensive understanding of the computational power of GNNs in node classification/regression tasks. Index Terms—Graph Neural Networks, Weisfeiler–Lehman, unfolding trees, graph theory, deep learning, message passing, expressive power.

The expressive power of Graph Neural Networks: a unifying point of view

Windows malware detectors based on machine learning are vulnerable to adversarial examples, even if the attacker is only given black-box query access to the model. The main drawback of these attacks is that: (i) they are query-inefficient, as they rely on iteratively applying random transformations to the input malware; and (ii) they may also require executing the adversarial malware in a sandbox at each iteration of the optimization process, to ensure that its intrusive functionality is preserved. In this paper, we overcome these issues by presenting a novel family of black-box attacks that are both query-efficient and functionality-preserving, as they rely on the injection of benign content - which will never be executed - either at the end of the malicious file, or within some newly-created sections. Our attacks are formalized as a constrained minimization problem which also enables optimizing the trade-off between the probability of evading detection and the size of the injected payload. We empirically investigate this trade-off on two popular static Windows malware detectors, and show that our black-box attacks can bypass them with only few queries and small payloads, even when they only return the predicted labels. We also evaluate whether our attacks transfer to other commercial antivirus solutions, and surprisingly find that they can evade, on average, more than 12 commercial antivirus engines. We conclude by discussing the limitations of our approach, and its possible future extensions to target malware classifiers based on dynamic analysis.

GAN-BERT: Semi-supervised Learning through Generative Adversarial Learning in Transformer-based Architectures

Downloads

Next from AIxIA 2021

Autonomous Development:Concepts and Challenges

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

GAN-BERT: Semi-supervised Learning through Generative Adversarial Learning in Transformer-based Architectures

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AIxIA 2021

Autonomous Development:Concepts and Challenges

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads