Imperial College London

ProfessorAlessandraRusso

Faculty of EngineeringDepartment of Computing

Professor in Applied Computational Logic
 
 
 
//

Contact

 

+44 (0)20 7594 8312a.russo Website

 
 
//

Location

 

560Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

206 results found

Koschate M, Naserian E, Dickens L, Stuart A, Russo A, Levine Met al., 2021, ASIA: Automated Social Identity Assessment using linguistic style, Behavior Research Methods, Vol: 53, Pages: 1762-1781, ISSN: 1554-351X

The various group and category memberships that we hold are at the heart of who we are. They have been shown to affect our thoughts, emotions, behavior, and social relations in a variety of social contexts, and have more recently been linked to our mental and physical well-being. Questions remain, however, over the dynamics between different group memberships and the ways in which we cognitively and emotionally acquire these. In particular, current assessment methods are missing that can be applied to naturally occurring data, such as online interactions, to better understand the dynamics and impact of group memberships in naturalistic settings. To provide researchers with a method for assessing specific group memberships of interest, we have developed ASIA (Automated Social Identity Assessment), an analytical protocol that uses linguistic style indicators in text to infer which group membership is salient in a given moment, accompanied by an in-depth open-source Jupyter Notebook tutorial (https://github.com/Identity-lab/Tutorial-on-salient-social-Identity-detection-model). Here, we first discuss the challenges in the study of salient group memberships, and how ASIA can address some of these. We then demonstrate how our analytical protocol can be used to create a method for assessing which of two specific group memberships—parents and feminists—is salient using online forum data, and how the quality (validity) of the measurement and its interpretation can be tested using two further corpora as well as an experimental study. We conclude by discussing future developments in the field.

Journal article

Law M, Russo A, Broda K, Bertino Eet al., 2021, Scalable non-observational predicate learning in ASP, IJCAI, Publisher: IJCAI, ISSN: 1045-0823

Recently, novel ILP systems under the answer set semantics have been proposed, some of which are robust to noise and scalable over large hypothesis spaces. One such system is FastLAS, which is significantly faster than other state-of-the-art ASP-based ILP systems. FastLAS is, however, only capable of Observational Predicate Learning (OPL),where the learned hypothesis defines predicates that are directly observed in the examples. It cannot learn knowledge that is indirectly observable, such as learning causes of observed events. This class of problems, known as non-OPL, is known to be difficult to handle in the context of non-monotonic semantics. Solving non-OPL learning tasks whilst preserving scalability is a challenging open problem. We address this problem with a new abductive method for translating examples of a non-OPL task to a set of examples, called possibilities, such that the original example is covered if at least one of the possibilities is covered. This new method al-lows an ILP system capable of performing OPL tasks to be “upgraded” to solve non-OPL tasks. In particular, we present our new FastNonOPL system, which upgrades FastLAS with the new possibility generation. We compare it to other state-of-the-art ASP-based ILP systems capable of solving non-OPL tasks, showing that FastNonOPL is significantly faster, and in many cases more accurate, than these other systems.

Conference paper

Furelos-Blanco D, Law M, Jonsson A, Broda K, Russo Aet al., 2021, Induction and exploitation of subgoal automata for reinforcement learning, Journal of Artificial Intelligence Research, Vol: 70, Pages: 1031-1116, ISSN: 1076-9757

In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks. ISA interleaves reinforcement learning with the induction of a subgoal automaton, an automaton whose edges are labeled by the task’s subgoals expressed as propositional logic formulas over a set of high-level events. A subgoal automaton also consists of two special states: a state indicating the successful completion of the task, and a state indicating that the task has finished without succeeding. A state-of-the-art inductive logic programming system is used to learn a subgoal automaton that covers the traces of high-level events observed by the RL agent. When the currently exploited automaton does not correctly recognize a trace, the automaton learner induces a new automaton that covers that trace. The interleaving process guarantees the induction of automata with the minimum number of states, and applies a symmetry breaking mechanism to shrink the search space whilst remaining complete. We evaluate ISA in several gridworld and continuous state space problems using different RL algorithms that leverage the automaton structures. We provide an in-depth empirical analysis of the automaton learning performance in terms of the traces, the symmetry breaking and specific restrictions imposed on the final learnable automaton. For each class of RL problem, we show that the learned automata can be successfully exploited to learn policies that reach the goal, achieving an average reward comparable to the case where automata are not learned but handcrafted and given beforehand.

Journal article

Al-Negheimish H, Madhyastha P, Russo A, 2021, Discrete reasoning templates for natural language understanding, Pages: 80-87

Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to simpler subquestions that can take advantage of single-span extraction reading-comprehension models, and derives the final answer according to instructions in a predefined reasoning template. We focus on subtraction based arithmetic questions and evaluate our approach on a subset of the DROP dataset. We show that our approach is competitive with the state of the art while being interpretable and requires little supervision.

Conference paper

Cingillioglu N, Russo A, 2020, Learning invariants through soft unification, Advances in Neural Information Processing Systems 33, ISSN: 1049-5258

Human reasoning involves recognising common underlying principles across many examples. The by-products of such reasoning are invariants that capture patterns such as “if someone went somewhere then they are there”, expressed using variables “someone” and “somewhere” instead of mentioning specific people or places. Humans learn what variables are and how to use them at a young age. This paper explores whether machines can also learn and use variables solely from examples without requiring human pre-engineering. We propose Unification Networks, an end-to-end differentiable neural network approach capable of lifting examples into invariants and using those invariants to solve a given task. The core characteristic of our architecture is soft unification between examples that enables the network to generalise parts of the input into variables, thereby learning invariants. We evaluate our approach on five datasets to demonstrate that learning invariants captures patterns in the data and can improve performance over baselines.

Conference paper

Ricca F, Russo A, 2020, Introduction to the 36th international conference on logic programming special issue II, THEORY AND PRACTICE OF LOGIC PROGRAMMING, Vol: 20, Pages: 815-817, ISSN: 1471-0684

This is the second issue with the selected papers of the 36th International Conference on LogicProgramming (ICLP 2020), held virtually in Rende (CS), Italy, from September 20 to September25, 2020. The two issues contain 27 papers selected from several tracks of the conference program for publication in Theory and Practice of Logic Programming. The preceding issue of thisvolume of the journal contains a detailed editorial by the conference chairs (?), as well as thefollowing fourteen papers selected for publication.

Journal article

Abu Jabal A, Bertino E, Lobo J, Law M, Russo A, Calo S, Verma Det al., 2020, Polisma - a framework for learning attribute-based access control policies, European Symposium on Research in Computer Security, Publisher: Springer International Publishing, Pages: 523-544, ISSN: 0302-9743

Attribute-based access control (ABAC) is being widely adopted due to its flexibility and universality in capturing authorizations in terms of the properties (attributes) of users and resources. However, specifying ABAC policies is a complex task due to the variety of such attributes. Moreover, migrating an access control system adopting a low-level model to ABAC can be challenging. An approach for generating ABAC policies is to learn them from data, namely from logs of historical access requests and their corresponding decisions. This paper proposes a novel framework for learning ABAC policies from data. The framework, referred to as Polisma, combines data mining, statistical, and machine learning techniques, capitalizing on potential context information obtained from external sources (e.g., LDAP directories) to enhance the learning process. The approach is evaluated empirically using two datasets (real and synthetic). Experimental results show that Polisma is able to generate ABAC policies that accurately control access requests and outperforms existing approaches.

Conference paper

Aspis Y, Broda K, Russo A, Lobo Jet al., 2020, Stable and supported semantics in continuous vector spaces, 17th International Conference on Principles of Knowledge Representation and Reasoning, KR 2020, Publisher: https://proceedings.kr.org/2020/7/, Pages: 58-67

We introduce a novel approach for the computation of stable and supported models of normal logic programs in continuous vector spaces by a gradient-based search method. Specifically, the application of the immediate consequence operator of a program reduct can be computed in a vector space. To do this, Herbrand interpretations of a propositional program are embedded as 0-1 vectors in R and program reducts are represented as matrices in ℝ . Using these representations we prove that the underlying semantics of a normal logic program is captured through matrix multiplication and a differentiable operation. As supported and stable models of a normal logic program can now be seen as fixed points in a continuous space, non-monotonic deduction can be performed using an optimisation process such as Newton's method. We report the results of several experiments using synthetically generated programs that demonstrate the feasibility of the approach and highlight how different parameter values can affect the behaviour of the system. N N×N

Conference paper

Ricca F, Russo A, 2020, Introduction to the 36th International Conference on Logic Programming Special Issue I, THEORY AND PRACTICE OF LOGIC PROGRAMMING, Vol: 20, Pages: 587-592, ISSN: 1471-0684

Journal article

Casale G, Artac M, van den Heuvel W-J, van Hoorn A, Jakovits P, Leymann F, Long M, Papanikolaou V, Presenza D, Russo A, Tamburri D, Wurster M, Zhu Let al., 2020, RADON: Rational decomposition and orchestration for serverless computing, SICS Software-Intensive Cyber-Physical Systems, Vol: 35, Pages: 77-87, ISSN: 2524-8529

Emerging serverless computing technologies, such as function as a service (FaaS), enable developers to virtualize the internal logic of an application, simplifying the management of cloud-native services and allowing cost savings through billing and scaling at the level of individual functions. Serverless computing is therefore rapidly shifting the attention of software vendors to the challenge of developing cloud applications deployable on FaaS platforms.In this vision paper, we present the research agendaof the RADON project (http://radon-h2020.eu),which aims to develop a model-driven DevOps framework for creating and managing applications based onserverless computing. RADON applications will consist of fine-grained and independent microservices that canefficiently and optimally exploit FaaS and containertechnologies. Our methodology strives to tackle complexity in designing such applications, including the solution of optimal decomposition, the reuse of serverlessfunctions as well as the abstraction and actuation ofevent processing chains, while avoiding cloud vendorlock-in through models.

Journal article

Gomoluch P, Alrajeh D, Russo A, Bucchiarone Aet al., 2020, Learning neural search policies for classical planning, International Conference on Automated Planning and Scheduling (ICAPS) 2020, Publisher: AAAI, Pages: 522-530, ISSN: 2334-0835

Heuristic forward search is currently the dominant paradigmin classical planning. Forward search algorithms typicallyrely on a single, relatively simple variation of best-first searchand remain fixed throughout the process of solving a plan-ning problem. Existing work combining multiple search tech-niques usually aims at supporting best-first search with anadditional exploratory mechanism, triggered using a hand-crafted criterion. A notable exception is very recent workwhich combines various search techniques using a trainablepolicy. That approach, however, is confined to a discrete ac-tion space comprising several fixed subroutines.In this paper, we introduce a parametrized search algorithmtemplate which combines various search techniques withina single routine. The template’s parameter space defines aninfinite space of search algorithms, including, among others,BFS, local and random search. We then propose a neural ar-chitecture for designating the values of the search parametersgiven the state of the search. This enables expressing neuralsearch policies that change the values of the parameters asthe search progresses. The policies can be learned automat-ically, with the objective of maximizing the planner’s per-formance on a given distribution of planning problems. Weconsider a training setting based on a stochastic optimizationalgorithm known as thecross-entropy method(CEM). Exper-imental evaluation of our approach shows that it is capable offinding effective distribution-specific search policies, outper-forming the relevant baselines.

Conference paper

Law M, Russo A, Bertino E, Broda K, Lobo Jet al., 2020, FastLAS: scalable inductive logic programming incorporating domain-specific optimisation criteria, The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-2020), Publisher: Association for the Advancement of ArtificialIntelligence, Pages: 2877-2885

Inductive Logic Programming (ILP) systems aim to find a setof logical rules, called a hypothesis, that explain a set of ex-amples. In cases where many such hypotheses exist, ILP sys-tems often bias towards shorter solutions, leading to highlygeneral rules being learned. In some application domains likesecurity and access control policies, this bias may not be de-sirable, as when data is sparse more specific rules that guaran-tee tighter security should be preferred. This paper presents anew general notion of ascoring functionover hypotheses thatallows a user to express domain-specific optimisation criteria.This is incorporated into a new ILP system, calledFastLAS,that takes as input a learning task and a customised scoringfunction, and computes an optimal solution with respect tothe given scoring function. We evaluate the accuracy of Fast-LAS over real-world datasets for access control policies andshow that varying the scoring function allows a user to tar-get domain-specific performance metrics. We also compareFastLAS to state-of-the-art ILP systems, using the standardILP bias for shorter solutions, and demonstrate that FastLASis significantly faster and more scalable.

Conference paper

Tuckey D, Broda K, Russo A, 2020, Towards Structure Learning under the Credal Semantics, ISSN: 1613-0073

We present the Credal-FOIL system for structure learning of probabilistic logic programs under the credal semantics. The credal semantics is a generalisation of the distribution semantics based on the answer set semantics. Our learning approach takes a set of examples that are atoms with target lower and upper bounds probabilities and a background knowledge that can have negative loops. We define accuracy in this setting and learn a set of normal rules without loops that maximises this notion of accuracy. We showcase the system on two proof-of-concept examples.

Conference paper

Furelos-Blanco D, Law M, Jonsson A, Broda K, Russo Aet al., 2020, Induction of Subgoal Automata for Reinforcement Learning, 34th AAAI Conference on Artificial Intelligence / 32nd Innovative Applications of Artificial Intelligence Conference / 10th AAAI Symposium on Educational Advances in Artificial Intelligence, Publisher: ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE, Pages: 3890-3897, ISSN: 2159-5399

Conference paper

Verma DC, Bertino E, Russo A, Calo S, Singla Aet al., 2020, Policy Based Ensembles for Multi Domain Operations, Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II Part of SPIE Defense + Commercial Sensing Conference, Publisher: SPIE-INT SOC OPTICAL ENGINEERING, ISSN: 0277-786X

Conference paper

White G, Cunnington D, Law M, Bertino E, De Mel G, Russo Aet al., 2019, A comparison between statistical and symbolic learning approaches for generative policy models, Pages: 1314-1321

Generative Policy Models (GPMs) have been proposed as a method for future autonomous decision making in a distributed, collaborative environment. To learn a GPM, previous policy examples that contain policy features and the corresponding policy decisions are used. Recently, GPMs have been constructed using both symbolic and statistical learning algorithms. In either case, the goal of the learning process is to create a model across a wide range of contexts from which specific policies may be generated in a given context. Empirically, we expect each learning approach to provide certain advantages over the other. This paper assesses the relative performance of each learning approach in order to examine these advantages and disadvantages. Several carefully prepared data sets are used to train a variety of models across different learning algorithms, where models for each learning algorithm are trained with varying amounts of labelled examples. The performance of each model is evaluated across a variety of metrics which indicates the strength of each learning algorithm for the different scenarios presented and the amount of training data provided. Finally, future research directions are outlined to fully realise GPMs in a distributed, collaborative environment.

Conference paper

Cunnington D, Manotas I, Law M, Mel GD, Calo S, Bertino E, Russo Aet al., 2019, A generative policy model for connected and autonomous vehicles, 2019 IEEE Intelligent Transportation Systems Conference - ITSC, Publisher: IEEE

Artificial Intelligence is rapidly enhancing human capability by providing support and guidance on a wide variety of tasks. However, one of the main challenges for autonomous systems is effectively managing the decisions and interactions between multiple entities in a dynamic environment. Policies are frequently used in cyber-physical systems to define target goals and constraints, such as maximising security whilst preventing communication to unauthorised systems. In this paper we introduce an approach for learning high-level policy models for future Connected and Autonomous Vehicles (CAVs). Since CAVs are required to operate in complex, safety-critical environments with a wide range of varying contextual conditions, high-level policies can help systems achieve their goals whilst adhering to varying environmental constraints. We present a Generative Policy Model (GPM) that enables a CAV to observe, learn, and adapt high-level policy models using local knowledge shared by related entities in the environment such as other CAVs, when reliable communication to traditional policy management systems may not be available. Within the proposed CAV GPM architecture, we utilise a novel context-free grammar bounded by a set of context-sensitive annotations called Answer Set Grammars (ASGs) and perform an evaluation of CAV policy generation in varying contexts. We also release the CAVPolicy dataset of annotated policies to enable future research in this area.

Conference paper

Russo A, Schuerr A, Wehrheim H, 2019, Editorial, FORMAL ASPECTS OF COMPUTING, Vol: 31, Pages: 457-458, ISSN: 0934-5043

Journal article

Bertino E, White G, Lobo J, Ingham J, Cirincione GH, Russo A, Law M, Calo S, Manotas I, Verma D, Jabal AA, Cunnington D, de Mel Get al., 2019, Generative policies for coalition systems - a symbolic learning framework, 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), Publisher: IEEE

Policy systems are critical for managing missions and collaborative activities carried out by coalitions involving different organizations. Conventional policy-based management approaches are not suitable for next-generation coalitions that will involve not only humans, but also autonomous computing devices and systems. It is critical that those parties be able to generate and customize policies based on contexts and activities. This paper introduces a novel approach for the autonomic generation of policies by autonomous parties. The framework combines context free grammars, answer set programs, and inductionbased learning. It allows a party to generate its own policies, based on a grammar and some semantic constraints, by learning from examples. The paper also outlines initial experiments in the use of such a symbolic approach and outlines relevant research challenges, ranging from explainability to quality assessment of policies.

Conference paper

Russo A, Schuerr A, 2019, Model-based software quality assurance tools and techniques presented at FASE 2018, INTERNATIONAL JOURNAL ON SOFTWARE TOOLS FOR TECHNOLOGY TRANSFER, Vol: 22, Pages: 1-2, ISSN: 1433-2779

Journal article

Law M, Russo A, Bertino E, Broda K, Lobo Jet al., 2019, Representing and learning grammars in answer set programming, AAAI-19: Thirty-third AAAI Conference on Artificial Intelligence, Publisher: Association for the Advancement of Artificial Intelligence, Pages: 2919-2928

In this paper we introduce an extension of context-free grammars called answer set grammars (ASGs). These grammars allow annotations on production rules, written in the language of Answer Set Programming (ASP), which can express context-sensitive constraints. We investigate the complexity of various classes of ASG with respect to two decision problems: deciding whether a given string belongs to the language of an ASG and deciding whether the language of an ASG is non-empty. Specifically, we show that the complexity of these decision problems can be lowered by restricting the subset of the ASP language used in the annotations. To aid the applicability of these grammars to computational problems that require context-sensitive parsers for partially known languages, we propose a learning task for inducing the annotations of an ASG. We characterise the complexity of this task and present an algorithm for solving it. An evaluation of a (prototype) implementation is also discussed.

Conference paper

Gomoluch P, Alrajeh D, Russo A, 2019, Learning classical planning strategies with policy gradient, International Conference on Automated Planning and Scheduling, Publisher: AAAI, Pages: 637-645, ISSN: 2334-0843

A common paradigm in classical planning is heuristic forwardsearch. Forward search planners often rely on simplebest-first search which remains fixed throughout the searchprocess. In this paper, we introduce a novel search frameworkcapable of alternating between several forward searchapproaches while solving a particular planning problem. Selectionof the approach is performed using a trainable stochasticpolicy, mapping the state of the search to a probability distributionover the approaches. This enables using policy gradientto learn search strategies tailored to a specific distributionsof planning problems and a selected performance metric,e.g. the IPC score. We instantiate the framework by constructinga policy space consisting of five search approachesand a two-dimensional representation of the planner’s state.Then, we train the system on randomly generated problemsfrom five IPC domains using three different performance metrics.Our experimental results show that the learner is ableto discover domain-specific search strategies, improving theplanner’s performance relative to the baselines of plain bestfirstsearch and a uniform policy.

Conference paper

Cingillioglu N, Russo A, 2019, DeepLogic: Towards end-to-end differentiable logical reasoning, AAAI 2019 Spring Symposium on Combining Machine Learning with Knowledge Engineering, Publisher: CEUR Workshop Proceedings, ISSN: 1613-0073

Combining machine learning with logic-based expert systems in order to get the best of both worlds are becoming increasingly popular. However, to what extent machine learning can already learn to reason over rule-based knowledge is still an open problem. In this paper, we explore how symbolic logic, defined as logic programs at a character level, is learned to be represented in a high-dimensional vector space using RNN-based iterative neural networks to perform reasoning. We create a new dataset that defines 12 classes of logic programs exemplifying increased level of complexity of logical reasoning and train the networks in an end-to-end fashion to learn whether a logic program entails a given query. We analyse how learning the inference algorithm gives rise to representations of atoms, literals and rules within logic programs and evaluate against increasing lengths of predicate and constant symbols as well as increasing steps of multi-hop reasoning.

Conference paper

Jabal AA, Davari M, Bertino E, Makaya C, Calo S, Verma D, Russo A, Williams Cet al., 2019, Methods and tools for policy analysis, ACM Computing Surveys, Vol: 51, ISSN: 0360-0300

Policy-based management of computer systems, computer networks and devices is a critical technology especially for present and future systems characterized by large-scale systems with autonomous devices, such as robots and drones. Maintaining reliable policy systems requires efficient and effective analysis approaches to ensure that the policies verify critical properties, such as correctness and consistency. In this paper, we present an extensive overview of methods for policy analysis. Then, we survey policy analysis systems and frameworks that have been proposed and compare them under various dimensions. We conclude the paper by outlining novel research directions in the area of policy analysis.

Journal article

Law M, Russo A, Broda K, 2019, Inductive Learning of Answer Set Programs from Noisy Examples, Advances in Cognitive Systems

Journal article

Calo S, Manotas I, de Mel G, Cunnington D, Law M, Verma D, Russo A, Bertino Eet al., 2019, AGENP: An ASGrammar-based GENerative Policy Framework, 23rd European Symposium on Research in Computer Security (ESORICS) / 2nd International Workshop on Policy-Based Autonomic Data Governance (PADG, Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 3-20, ISSN: 0302-9743

Conference paper

Law M, Russo A, Broda K, 2019, Logic-Based Learning of Answer Set Programs, Pages: 196-231, ISSN: 0302-9743

Learning interpretable models from data is stated as one of the main challenges of AI. The goal of logic-based learning is to compute interpretable (logic) programs that explain labelled examples in the context of given background knowledge. This tutorial introduces recent advances of logic-based learning, specifically learning non-monotonic logic programs under the answer set semantics. We introduce several learning frameworks and algorithms, which allow for learning highly expressive programs, containing rules representing non-determinism, choice, exceptions, constraints and preferences. Throughout the tutorial, we put a strong emphasis on the expressive power of the learning systems and frameworks, explaining why some systems are incapable of learning particular classes of programs.

Conference paper

Verma D, Calo S, Bertino E, Russo A, White Get al., 2019, Policy based Ensembles for applying ML on Big Data, IEEE International Conference on Big Data (Big Data), Publisher: IEEE, Pages: 4038-4044, ISSN: 2639-1589

Conference paper

Cunnington D, Law M, Russo A, Bertino E, Calo Set al., 2019, Towards a Neural-Symbolic Generative Policy Model, IEEE International Conference on Big Data (Big Data), Publisher: IEEE, Pages: 4008-4016, ISSN: 2639-1589

Conference paper

White G, Ingham J, Law M, Russo Aet al., 2019, Using an ASG based Generative Policy to Model Human Rules, 5th IEEE International Conference on Smart Computing (SMARTCOMP), Publisher: IEEE, Pages: 99-103

Conference paper

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: respub-action=search.html&id=00157171&limit=30&person=true