1,721,117 research outputs found
Special issue: Selected and revised papers from the 17th International Conference of the Italian Association for Artificial Intelligence
No full textInterpretability Is in the Mind of the Beholder: A Causal Framework for Human-Interpretable Representation Learning
No full textResearch on Explainable Artificial Intelligence has recently started exploring the idea of producing explanations that, rather than being expressed in terms of low-level features, are encoded in terms of interpretable concepts learned from data. How to reliably acquire such concepts is, however, still fundamentally unclear. An agreed-upon notion of concept interpretability is missing, with the result that concepts used by both post hoc explainers and concept-based neural networks are acquired through a variety of mutually incompatible strategies. Critically, most of these neglect the human side of the problem: a representation is understandable only insofar as it can be understood by the human at the receiving end. The key challenge in human-interpretable representation learning (hrl) is how to model and operationalize this human element. In this work, we propose a mathematical framework for acquiring interpretable representations suitable for both post hoc explainers and concept-based neural networks. Our formalization of hrl builds on recent advances in causal representation learning and explicitly models a human stakeholder as an external observer. This allows us derive a principled notion of alignment between the machine’s representation and the vocabulary of concepts understood by the human. In doing so, we link alignment and interpretability through a simple and intuitive name transfer game, and clarify the relationship between alignment and a well-known property of representations, namely disentanglement. We also show that alignment is linked to the issue of undesirable correlations among concepts, also known as concept leakage, and to content-style separation, all through a general information-theoretic reformulation of these properties. Our conceptualization aims to bridge the gap between the human and algorithmic sides of interpretability and establish a stepping stone for new research on human-interpretable representations
Personality traits and the role of gender in swimmers at the leisure level
Full text linkAbstract: We used the Big Five Questionnaire (BFQ; Caprara, Barbaranelli, & Borgogni, 1993) with swimmers engaged in indoor practice at the leisure level (50 male, 50 female) to measure whether personality traits are associated with swimming. We also examined the concept that scores on some personality traits can have a reciprocal closely intermingled influence on other personality traits, and that gender can play a role in modulating personality. We found that the swimmers were characterized by evidence of personality traits distributed within moderate middle scores in personality factors, contributing to well-being and satisfaction with life. We also found correlations within factors and subfactors, showing a close relationship among personality traits. Gender also plays a role in the measurement of personality traits as gender has a statistically significant effect on extraversion
A Big Data and machine learning approach for network monitoring and security
Full text linkIn the last decade the performances of 802.11 (Wi-Fi) devices skyrocketed. Today it is possible to realize gigabit wireless links spanning across kilometers at a fraction of the cost of the wired equivalent. In the same period, mesh network evolved from being experimental tools confined into university labs, to systems running in several real world scenarios. Mesh networks can now provide city-wide coverage and can compete on the market of Internet access. Yet, being wireless distributed networks, mesh networks are still hard to maintain and monitor. This paper explains how today we can perform monitoring, anomaly detection and root cause analysis in mesh networks using Big Data techniques. It first describes the architecture of a modern mesh network, it justifies the use of Big Data techniques and provides a design for the storage and analysis of Big Data produced by a large-scale mesh network. While proposing a generic infrastructure, we focus on its application in the security domain
An efficient procedure for mining egocentric temporal motifs
No full textTemporal graphs are structures which model relational data between entities that change over time. Due to the complex structure of data, mining statistically significant temporal subgraphs, also known as temporal motifs, is a challenging task. In this work, we present an efficient technique for extracting temporal motifs in temporal networks. Our method is based on the novel notion of egocentric temporal neighborhoods, namely multi-layer structures centered on an ego node. Each temporal layer of the structure consists of the first-order neighborhood of the ego node, and corresponding nodes in sequential layers are connected by an edge. The strength of this approach lies in the possibility of encoding these structures into a unique bit vector, thus bypassing the problem of graph isomorphism in searching for temporal motifs. This allows our algorithm to mine substantially larger motifs with respect to alternative approaches. Furthermore, by bringing the focus on the temporal dynamics of the interactions of a specific node, our model allows to mine temporal motifs which are visibly interpretable. Experiments on a number of complex networks of social interactions confirm the advantage of the proposed approach over alternative non-egocentric solutions. The egocentric procedure is indeed more efficient in revealing similarities and discrepancies among different social environments, independently of the different technologies used to collect data, which instead affect standard non-egocentric measures
MetalDetector v2.0: Predicting the geometry of metal binding sites from protein sequence
Full text linkMetalDetector identifies CYS and HIS involved in transition metal protein binding sites, starting from sequence alone. A major new feature of release 2.0 is the ability to predict which residues are jointly involved in the coordination of the same metal ion. The server is available at http://metaldetector.dsi.unifi.it/v2.0/. © 2011 The Author(s)
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
No full textBeing able to provide counterfactual interventions - sequences of actions we
would have had to take for a desirable outcome to happen - is essential to
explain how to change an unfavourable decision by a black-box machine learning
model (e.g., being denied a loan request). Existing solutions have mainly
focused on generating feasible interventions without providing explanations on
their rationale. Moreover, they need to solve a separate optimization problem
for each user. In this paper, we take a different approach and learn a program
that outputs a sequence of explainable counterfactual actions given a user
description and a causal graph. We leverage program synthesis techniques,
reinforcement learning coupled with Monte Carlo Tree Search for efficient
exploration, and rule learning to extract explanations for each recommended
action. An experimental evaluation on synthetic and real-world datasets shows
how our approach generates effective interventions by making orders of
magnitude fewer queries to the black-box classifier with respect to existing
solutions, with the additional benefit of complementing them with interpretable
explanations
GlanceNets: Interpretabile, Leak-proof Concept-based Models
No full textThere is growing interest in concept-based models (CBMs) that combine highperformance and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A key requirement is that the concepts be interpretable. Existing CBMs tackle this desideratum using a variety of heuristics based on unclear notions of interpretability, and fail to acquire concepts with the intended semantics. We address this by providing a clear definition of interpretability in terms of alignment between the model’s representation and an underlying data generation
process, and introduce GlanceNets, a new CBM that exploits techniques from disentangled representation learning and open-set recognition to achieve alignment, thus improving the interpretability of the learned concepts. We show that GlanceNets, paired with concept-level supervision, achieve better alignment than state-of-the-art approaches while preventing spurious concepts from unintentionally affecting its predictions. The code is available at https://github.com/ema-marconato/glancenet
- …
