arXiv subjects

Francesca Rossi

Publications and source records attributed to Francesca Rossi.

At least 55 records · Page 3Linked to original sources

arXiv2020

Thinking Fast and Slow in AI

This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making. The premise is that if we gain insights about the causes of some human capabilities that are still lacking in AI (for instance, adaptability, generalizability, common sense, and causal reasoning), we may obtain similar capabilities in an AI system by embedding these causal components. We hope that the high-level description of our vision included in this paper, as well as the several research questions that we propose to consider, can stimulate the AI research community to define, try and evaluate new methodologies, frameworks, and evaluation metrics, in the spirit of achieving a better understanding of both human and machine intelligence.

cs.AI↗

arXiv2020

Personalized Chatbot Trustworthiness Ratings

Conversation agents, commonly referred to as chatbots, are increasingly deployed in many domains to allow people to have a natural interaction while trying to solve a specific problem. Given their widespread use, it is important to provide their users with methods and tools to increase users awareness of various properties of the chatbots, including non-functional properties that users may consider important in order to trust a specific chatbot. For example, users may want to use chatbots that are not biased, that do not use abusive language, that do not leak information to other users, and that respond in a style which is appropriate for the user's cognitive level. In this paper, we address the setting where a chatbot cannot be modified, its training data cannot be accessed, and yet a neutral party wants to assess and communicate its trustworthiness to a user, tailored to the user's priorities over the various trust issues. Such a rating can help users choose among alternative chatbots, developers test their systems, business leaders price their offering, and regulators set policies. We envision a personalized rating methodology for chatbots that relies on separate rating modules for each issue, and users' detected priority orderings among the relevant trust issues, to generate an aggregate personalized rating for the trustworthiness of a chatbot. The method is independent of the specific trust issues and is parametric to the aggregation procedure, thereby allowing for seamless generalization. We illustrate its general use, integrate it with a live chatbot, and evaluate it on four dialog datasets and representative user profiles, validated with user surveys.

cs.SI↗

arXiv2020

Learning and Recognizing Archeological Features from LiDAR Data

We present a remote sensing pipeline that processes LiDAR (Light Detection And Ranging) data through machine & deep learning for the application of archeological feature detection on big geo-spatial data platforms such as e.g. IBM PAIRS Geoscope. Today, archeologists get overwhelmed by the task of visually surveying huge amounts of (raw) LiDAR data in order to identify areas of interest for inspection on the ground. We showcase a software system pipeline that results in significant savings in terms of expert productivity while missing only a small fraction of the artifacts. Our work employs artificial neural networks in conjunction with an efficient spatial segmentation procedure based on domain knowledge. Data processing is constraint by a limited amount of training labels and noisy LiDAR signals due to vegetation cover and decay of ancient structures. We aim at identifying geo-spatial areas with archeological artifacts in a supervised fashion allowing the domain expert to flexibly tune parameters based on her needs.

cs.CV↗

arXiv2020

Modeling Contrary-to-Duty with CP-nets

In a ceteris-paribus semantics for deontic logic, a state of affairs where a larger set of prescriptions is respected is preferable to a state of affairs where some of them are violated. Conditional preference nets (CP-nets) are a compact formalism to express and analyse ceteris paribus preferences, which nice computational properties. This paper shows how deontic concepts can be captured through conditional preference models. A restricted deontic logic will be defined, and mapped into conditional preference nets. We shall also show how to model contrary to duties obligations in CP-nets and how to capture in this formalism the distinction between strong and weak permission.

cs.AI↗

arXiv2020

Orbital Tuning of Tunnel Coupling in InAs/InP Nanowire Quantum Dots

We report results on the control of barrier transparency in InAs/InP nanowire quantum dots via the electrostatic control of the device electron states. Recent works demonstrated that barrier transparency in this class of devices displays a general trend just depending on the total orbital energy of the trapped electrons. We show that a qualitatively different regime is observed at relatively low filling numbers, where tunneling rates are rather controlled by the axial configuration of the electron orbital. Transmission rates versus filling are further modified by acting on the radial configuration of the orbitals by means of electrostatic gating, and the barrier transparency for the various orbitals is found to evolve as expected from numerical simulations. The possibility to exploit this mechanism to achieve a controlled continuous tuning of the tunneling rate of an individual Coulomb blockade resonance is discussed.

cond-mat.mes-hall↗

arXiv2020

Probing proximity induced superconductivity in InAs nanowire using built-in barriers

Bound states in superconductor-nanowire hybrid devices play a central role, carrying informationon the ground states properties (Shiba or Andreev states) or on the topological properties of thesystem (Majorana states). The spectroscopy of such bound states relies on the formation of well-defined tunnel barriers, usually defined by gate electrodes, which results in smooth tunnel barriers.Here we used thin InP segments embedded into InAs nanowire during the growth process to forma sharp built-in tunnel barrier. Gate dependence and thermal activation measurements have beenused to confirm the presence and estimate the height of this barrier. By coupling these wires tosuperconducting electrodes we have investigated the gate voltage dependence of the induced gap inthe nanowire segment, which we could understand using a simple model based on Andreev boundstates. Our results show that these built-in barriers are promising as future spectroscopic tools

cond-mat.mes-hall↗

arXiv2019

Highly symmetric and tunable tunnel couplings in InAs/InP nanowire heterostructure quantum dots

We present a comprehensive electrical characterization of an InAs/InP nanowire heterostructure, comprising two InP barriers forming a quantum dot (QD), two adjacent lead segments (LSs) and two metallic contacts, and demonstrate how to extract valuable quantitative information of the QD. The QD shows very regular Coulomb blockade (CB) resonances over a large gate voltage range. By analyzing the resonance line shapes, we map the evolution of the tunnel couplings from the few to the many electron regime, with electrically tunable tunnel couplings from <1 $μ$eV to >600 $μ$eV, and a transition from the temperature to the lifetime broadened regime. The InP segments form tunnel barriers with almost fully symmetric tunnel couplings and a barrier height of ~350 meV. All of these findings can be understood in great detail based on the deterministic material composition and geometry. Our results demonstrate that integrated InAs/InP QDs provide a promising platform for electron tunneling spectroscopy in InAs nanowires, which can readily be contacted by a variety of superconducting materials to investigate subgap states in proximitized NW regions, or be used to characterize thermoelectric nanoscale devices in the quantum regime.

cond-mat.mes-hall↗

arXiv2019

CPMetric: Deep Siamese Networks for Learning Distances Between Structured Preferences

Preference are central to decision making by both machines and humans. Representing, learning, and reasoning with preferences is an important area of study both within computer science and across the sciences. When working with preferences it is necessary to understand and compute the distance between sets of objects, e.g., the preferences of a user and a the descriptions of objects to be recommended. We present CPDist, a novel neural network to address the problem of learning to measure the distance between structured preference representations. We use the popular CP-net formalism to represent preferences and then leverage deep neural networks to learn a recently proposed metric function that is computationally hard to compute directly. CPDist is a novel metric learning approach based on the use of deep siamese networks which learn the Kendal Tau distance between partial orders that are induced by compact preference representations. We find that CPDist is able to learn the distance function with high accuracy and outperform existing approximation algorithms on both the regression and classification task using less computation time. Performance remains good even when CPDist is trained with only a small number of samples compared to the dimension of the solution space, indicating the network generalizes well.

cs.LG↗

arXiv2019

Towards Composable Bias Rating of AI Services

A new wave of decision-support systems are being built today using AI services that draw insights from data (like text and video) and incorporate them in human-in-the-loop assistance. However, just as we expect humans to be ethical, the same expectation needs to be met by automated systems that increasingly get delegated to act on their behalf. A very important aspect of an ethical behavior is to avoid (intended, perceived, or accidental) bias. Bias occurs when the data distribution is not representative enough of the natural phenomenon one wants to model and reason about. The possibly biased behavior of a service is hard to detect and handle if the AI service is merely being used and not developed from scratch, since the training data set is not available. In this situation, we envisage a 3rd party rating agency that is independent of the API producer or consumer and has its own set of biased and unbiased data, with customizable distributions. We propose a 2-step rating approach that generates bias ratings signifying whether the AI service is unbiased compensating, data-sensitive biased, or biased. The approach also works on composite services. We implement it in the context of text translation and report interesting results.

cs.AI↗

arXiv2018

Using deceased-donor kidneys to initiate chains of living donor kidney paired donations: algorithms and experimentation

We design a flexible algorithm that exploits deceased donor kidneys to initiate chains of living donor kidney paired donations, combining deceased and living donor allocation mechanisms to improve the quantity and quality of kidney transplants. The advantages of this approach have been measured using retrospective data on the pool of donor/recipient incompatible and desensitized pairs at the Padua University Hospital, the largest center for living donor kidney transplants in Italy. The experiments show a remarkable improvement on the number of patients with incompatible donor who could be transplanted, a decrease in the number of desensitization procedures, and an increase in the number of UT patients (that is, patients unlikely to be transplanted for immunological reasons) in the waiting list who could receive an organ.

q-bio.TO↗

arXiv2018

Building Ethically Bounded AI

The more AI agents are deployed in scenarios with possibly unexpected situations, the more they need to be flexible, adaptive, and creative in achieving the goal we have given them. Thus, a certain level of freedom to choose the best path to the goal is inherent in making AI robust and flexible enough. At the same time, however, the pervasive deployment of AI in our life, whether AI is autonomous or collaborating with humans, raises several ethical challenges. AI agents should be aware and follow appropriate ethical principles and should thus exhibit properties such as fairness or other virtues. These ethical principles should define the boundaries of AI's freedom and creativity. However, it is still a challenge to understand how to specify and reason with ethical boundaries in AI agents and how to combine them appropriately with subjective preferences and goal specifications. Some initial attempts employ either a data-driven example-based approach for both, or a symbolic rule-based approach for both. We envision a modular approach where any AI technique can be used for any of these essential ingredients in decision making or decision support systems, paired with a contextual approach to define their combination and relative weight. In a world where neither humans nor AI systems work in isolation, but are tightly interconnected, e.g., the Internet of Things, we also envision a compositional approach to building ethically bounded AI, where the ethical properties of each component can be fruitfully exploited to derive those of the overall system. In this paper we define and motivate the notion of ethically-bounded AI, we describe two concrete examples, and we outline some outstanding challenges.

cs.AI↗

arXiv2018

Interpretable Multi-Objective Reinforcement Learning through Policy Orchestration

Autonomous cyber-physical agents and systems play an increasingly large role in our lives. To ensure that agents behave in ways aligned with the values of the societies in which they operate, we must develop techniques that allow these agents to not only maximize their reward in an environment, but also to learn and follow the implicit constraints of society. These constraints and norms can come from any number of sources including regulations, business process guidelines, laws, ethical principles, social norms, and moral values. We detail a novel approach that uses inverse reinforcement learning to learn a set of unspecified constraints from demonstrations of the task, and reinforcement learning to learn to maximize the environment rewards. More precisely, we assume that an agent can observe traces of behavior of members of the society but has no access to the explicit set of constraints that give rise to the observed behavior. Inverse reinforcement learning is used to learn such constraints, that are then combined with a possibly orthogonal value function through the use of a contextual bandit-based orchestrator that picks a contextually-appropriate choice between the two policies (constraint-based and environment reward-based) when taking actions. The contextual bandit orchestrator allows the agent to mix policies in novel ways, taking the best actions from either a reward maximizing or constrained policy. In addition, the orchestrator is transparent on which policy is being employed at each time step. We test our algorithms using a Pac-Man domain and show that the agent is able to learn to act optimally, act within the demonstrated constraints, and mix these two functions in complex ways.

cs.LG↗

arXiv2018

Incorporating Behavioral Constraints in Online AI Systems

AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding criteria, as there are additional constraints and/or priorities imposed by regulations, values, preferences, or ethical principles. We detail a novel online agent that learns a set of behavioral constraints by observation and uses these learned constraints as a guide when making decisions in an online setting while still being reactive to reward feedback. To define this agent, we propose to adopt a novel extension to the classical contextual multi-armed bandit setting and we provide a new algorithm called Behavior Constrained Thompson Sampling (BCTS) that allows for online learning while obeying exogenous constraints. Our agent learns a constrained policy that implements the observed behavioral constraints demonstrated by a teacher agent, and then uses this constrained policy to guide the reward-based online exploration and exploitation. We characterize the upper bound on the expected regret of the contextual bandit algorithm that underlies our agent and provide a case study with real world data in two application domains. Our experiments show that the designed agent is able to act within the set of behavior constraints without significantly degrading its overall reward performance.

cs.AI↗

arXiv2017

Cognitive Hierarchy and Voting Manipulation

By the Gibbard--Satterthwaite theorem, every reasonable voting rule for three or more alternatives is susceptible to manipulation: there exist elections where one or more voters can change the election outcome in their favour by unilaterally modifying their vote. When a given election admits several such voters, strategic voting becomes a game among potential manipulators: a manipulative vote that leads to a better outcome when other voters are truthful may lead to disastrous results when other voters choose to manipulate as well. We consider this situation from the perspective of a boundedly rational voter, and use the cognitive hierarchy framework to identify good strategies. We then investigate the associated algorithmic questions under the k-approval voting rule. We obtain positive algorithmic results for k=1 and 2, and NP- and coNP-hardness results for k>3.

cs.GT↗

arXiv2017

Gibbard-Satterthwaite Games for k-Approval Voting Rules

The Gibbard-Satterthwaite theorem implies the existence of voters, called manipulators, who can change the election outcome in their favour by voting strategically. When a given preference profile admits several such manipulators, voting becomes a game played by these voters, who have to reason strategically about each others' actions. To complicate the game even further, counter-manipulators may then try to counteract the actions of manipulators. Our voters are boundedly rational and do not think beyond manipulating or countermanipulating. We call these games Gibbard--Satterthwaite Games. In this paper we look for conditions that guarantee the existence of a Nash equilibria in pure strategies.

cs.GT↗

arXiv2013

Restricted Manipulation in Iterative Voting: Convergence and Condorcet Efficiency

In collective decision making, where a voting rule is used to take a collective decision among a group of agents, manipulation by one or more agents is usually considered negative behavior to be avoided, or at least to be made computationally difficult for the agents to perform. However, there are scenarios in which a restricted form of manipulation can instead be beneficial. In this paper we consider the iterative version of several voting rules, where at each step one agent is allowed to manipulate by modifying his ballot according to a set of restricted manipulation moves which are computationally easy and require little information to be performed. We prove convergence of iterative voting rules when restricted manipulation is allowed, and we present experiments showing that most iterative voting rules have a higher Condorcet efficiency than their non-iterative version.

cs.AI↗

arXiv2010

Stable marriage problems with quantitative preferences

The stable marriage problem is a well-known problem of matching men to women so that no man and woman, who are not married to each other, both prefer each other. Such a problem has a wide variety of practical applications, ranging from matching resident doctors to hospitals, to matching students to schools or more generally to any two-sided market. In the classical stable marriage problem, both men and women express a strict preference order over the members of the other sex, in a qualitative way. Here we consider stable marriage problems with quantitative preferences: each man (resp., woman) provides a score for each woman (resp., man). Such problems are more expressive than the classical stable marriage problems. Moreover, in some real-life situations it is more natural to express scores (to model, for example, profits or costs) rather than a qualitative preference ordering. In this context, we define new notions of stability and optimality, and we provide algorithms to find marriages which are stable and/or optimal according to these notions. While expressivity greatly increases by adopting quantitative preferences, we show that in most cases the desired solutions can be found by adapting existing algorithms for the classical stable marriage problem.

cs.AI↗

arXiv2009

Manipulation and gender neutrality in stable marriage procedures

The stable marriage problem is a well-known problem of matching men to women so that no man and woman who are not married to each other both prefer each other. Such a problem has a wide variety of practical applications ranging from matching resident doctors to hospitals to matching students to schools. A well-known algorithm to solve this problem is the Gale-Shapley algorithm, which runs in polynomial time. It has been proven that stable marriage procedures can always be manipulated. Whilst the Gale-Shapley algorithm is computationally easy to manipulate, we prove that there exist stable marriage procedures which are NP-hard to manipulate. We also consider the relationship between voting theory and stable marriage procedures, showing that voting rules which are NP-hard to manipulate can be used to define stable marriage procedures which are themselves NP-hard to manipulate. Finally, we consider the issue that stable marriage procedures like Gale-Shapley favour one gender over the other, and we show how to use voting rules to make any stable marriage procedure gender neutral.

cs.AI↗