Self-supervised information retrieval: a novel approach based on Deep Metric Learning and Neural Language Models

Most of the existing open-source search engines, utilize keyword or tf-idf based techniques to find relevant documents and web pages relative to an input query. Although these methods, with the help of a page rank or knowledge graphs, proved to be effective in some cases, they often fail to retrieve relevant instances for more complicated queries that would require a semantic understanding to be exploited. In this Thesis, a self-supervised information retrieval system based on transformers is employed to build a semantic search engine over the library of Gruppo Maggioli company. Semantic search or search with meaning can refer to an understanding of the query, instead of simply finding words matches and, in general, it represents knowledge in a way suitable for retrieval. We chose to investigate a new self-supervised strategy to handle the training of unlabeled data based on the creation of pairs of ’artificial’ queries and the respective positive passages. We claim that by removing the reliance on labeled data, we may use the large volume of unlabeled material on the web without being limited to languages or domains where labeled data is abundant.

LQG control policy design against agent identity privacy problem

This thesis project studies the agent identity privacy problem in the scalar linear quadratic Gaussian (LQG) control system. For the agent identity privacy problem in the LQG control, privacy models and privacy measures have to be established first. It depends on a trajectory of correlated data rather than a single observation. I propose here privacy models and the corresponding privacy measures by taking into account the two characteristics. The agent identity is a binary hypothesis: Agent A or Agent B. An eavesdropper is assumed to make a hypothesis testing on the agent identity based on the intercepted environment state sequence. The privacy risk is measured by the Kullback-Leibler divergence between the probability distributions of state sequences under two hypotheses. By taking into account both the accumulative control reward and privacy risk, an optimization problem of the policy of Agent B is formulated. The optimal deterministic privacy-preserving LQG policy of Agent B is a linear mapping. A sufficient condition is given to guarantee that the optimal deterministic privacy-preserving policy is time-invariant in the asymptotic regime. An independent Gaussian random variable cannot improve the performance of Agent B. The numerical experiments justify the theoretic results and illustrate the reward-privacy trade-off. Based on the privacy model and the LQG control model, I have formulated the mathematical problems for the agent identity privacy problem in LQG. The formulated problems address the two design objectives: to maximize the control reward and to minimize the privacy risk. I have conducted theoretic analysis on the LQG control policy in the agent identity privacy problem and the trade-off between the control reward and the privacy risk.Finally, the theoretic results are justified by numerical experiments. From the numerical results, I expected to have some interesting observations and insights, which are explained in the last chapter.

Bio-QA-GNN: Reasoning with Language Models and Knowledge Graphs for Interpretable Biomedical Question Answering

Nowadays the idea of injecting world or domain-specific structured knowledge into pre-trained language models (PLMs) is becoming an increasingly popular approach for solving problems such as biases, hallucinations, huge architectural sizes, and explainability lack—critical for real-world natural language processing applications in sensitive fields like bioinformatics. One recent work that has garnered much attention in Neuro-symbolic AI is QA-GNN, an end-to-end model for multiple-choice open-domain question answering (MCOQA) tasks via interpretable text-graph reasoning. Unlike previous publications, QA-GNN mutually informs PLMs and graph neural networks (GNNs) on top of relevant facts retrieved from knowledge graphs (KGs). However, taking a more holistic view, existing PLM+KG contributions mainly consider commonsense benchmarks and ignore or shallowly analyze performances on biomedical datasets. This thesis start from a propose of a deep investigation of QA-GNN for biomedicine, comparing existing or brand-new PLMs, KGs, edge-aware GNNs, preprocessing techniques, and initialization strategies. By combining the insights emerged in DISI's research, we introduce Bio-QA-GNN that include a KG. Working with this part has led to an improvement in state-of-the-art of MCOQA model on biomedical/clinical text, largely outperforming the original one (+3.63\% accuracy on MedQA). Our findings also contribute to a better understanding of the explanation degree allowed by joint text-graph reasoning architectures and their effectiveness on different medical subjects and reasoning types. Codes, models, datasets, and demos to reproduce the results are freely available at: \url{https://github.com/disi-unibo-nlp/bio-qagnn}.

Optimal robust estimates using the Hellinger distance

Optimal robust M-estimates of a multidimensional parameter are described using Hampel's infinitesimal approach. The optimal estimates are derived by minimizing a measure of efficiency under the model, subject to a bounded measure of infinitesimal robustness. To this purpose we define measures of efficiency and infinitesimal sensitivity based on the Hellinger distance.We show that these two measures coincide with similar ones defined by Yohai using the Kullback-Leibler divergence, and therefore the corresponding optimal estimates coincide too.We also give an example where we fit a negative binomial distribution to a real dataset of "days of stay in hospital" using the optimal robust estimates.

On the relationship between connections and the asymptotic properties of predictive distributions

In a recent paper, Komaki studied the second-order asymptotic properties of predictive distributions, using the Kullback-Leibler divergence as a loss function. He showed that estimative distributions with asymptotically efficient estimators can be improved by predictive distributions that do not belong to the model. The model is assumed to be a multidimensional curved exponential family. In this paper we generalize the result assuming as a loss function any f divergence. A relationship arises between alpha connections and optimal predictive distributions. In particular, using an alpha divergence to measure the goodness of a predictive distribution, the optimal shift of the estimate distribution is related to alpha-covariant derivatives. The expression that we obtain for the asymptotic risk is also useful to study the higher-order asymptotic properties of an estimator, in the mentioned class of loss functions.

Segmentação Fuzzy de Texturas e Vídeos

The segmentation of an image aims to subdivide it into constituent regions or objects that have some relevant semantic content. This subdivision can also be applied to videos. However, in these cases, the objects appear in various frames that compose the videos. The task of segmenting an image becomes more complex when they are composed of objects that are defined by textural features, where the color information alone is not a good descriptor of the image. Fuzzy Segmentation is a region-growing segmentation algorithm that uses affinity functions in order to assign to each element in an image a grade of membership for each object (between 0 and 1). This work presents a modification of the Fuzzy Segmentation algorithm, for the purpose of improving the temporal and spatial complexity. The algorithm was adapted to segmenting color videos, treating them as 3D volume. In order to perform segmentation in videos, conventional color model or a hybrid model obtained by a method for choosing the best channels were used. The Fuzzy Segmentation algorithm was also applied to texture segmentation by using adaptive affinity functions defined for each object texture. Two types of affinity functions were used, one defined using the normal (or Gaussian) probability distribution and the other using the Skew Divergence. This latter, a Kullback-Leibler Divergence variation, is a measure of the difference between two probability distributions. Finally, the algorithm was tested in somes videos and also in texture mosaic images composed by images of the Brodatz album

The FGM bivariate lifetime copula model: a bayesian approach

In this paper, we propose a bivariate distribution for the bivariate survival times based on Farlie-Gumbel-Morgenstern copula to model the dependence on a bivariate survival data. The proposed model allows for the presence of censored data and covariates. For inferential purpose a Bayesian approach via Markov Chain Monte Carlo (MCMC) is considered. Further, some discussions on the model selection criteria are given. In order to examine outlying and influential observations, we present a Bayesian case deletion influence diagnostics based on the Kullback-Leibler divergence. The newly developed procedures are illustrated via a simulation study and a real dataset.

Time series irreversibility: a visibility graph approach

We propose a method to measure real-valued time series irreversibility which combines two different tools: the horizontal visibility algorithm and the Kullback-Leibler divergence. This method maps a time series to a directed network according to a geometric criterion. The degree of irreversibility of the series is then estimated by the Kullback-Leibler divergence (i.e. the distinguishability) between the in and out degree distributions of the associated graph. The method is computationally efficient and does not require any ad hoc symbolization process. We find that the method correctly distinguishes between reversible and irreversible stationary time series, including analytical and numerical studies of its performance for: (i) reversible stochastic processes (uncorrelated and Gaussian linearly correlated), (ii) irreversible stochastic processes (a discrete flashing ratchet in an asymmetric potential), (iii) reversible (conservative) and irreversible (dissipative) chaotic maps, and (iv) dissipative chaotic maps in the presence of noise. Two alternative graph functionals, the degree and the degree-degree distributions, can be used as the Kullback-Leibler divergence argument. The former is simpler and more intuitive and can be used as a benchmark, but in the case of an irreversible process with null net current, the degree-degree distribution has to be considered to identify the irreversible nature of the series

Camera localization using trajectories and maps

We propose a new Bayesian framework for automatically determining the position (location and orientation) of an uncalibrated camera using the observations of moving objects and a schematic map of the passable areas of the environment. Our approach takes advantage of static and dynamic information on the scene structures through prior probability distributions for object dynamics. The proposed approach restricts plausible positions where the sensor can be located while taking into account the inherent ambiguity of the given setting. The proposed framework samples from the posterior probability distribution for the camera position via data driven MCMC, guided by an initial geometric analysis that restricts the search space. A Kullback-Leibler divergence analysis is then used that yields the final camera position estimate, while explicitly isolating ambiguous settings. The proposed approach is evaluated in synthetic and real environments, showing its satisfactory performance in both ambiguous and unambiguous settings.

Population-based continuous optimization, probabilistic modelling and mean shift

Evolutionary algorithms perform optimization using a population of sample solution points. An interesting development has been to view population-based optimization as the process of evolving an explicit, probabilistic model of the search space. This paper investigates a formal basis for continuous, population-based optimization in terms of a stochastic gradient descent on the Kullback-Leibler divergence between the model probability density and the objective function, represented as an unknown density of assumed form. This leads to an update rule that is related and compared with previous theoretical work, a continuous version of the population-based incremental learning algorithm, and the generalized mean shift clustering framework. Experimental results are presented that demonstrate the dynamics of the new algorithm on a set of simple test problems.

Fully probabilistic control design in an adaptive critic framework

Optimal stochastic controller pushes the closed-loop behavior as close as possible to the desired one. The fully probabilistic design (FPD) uses probabilistic description of the desired closed loop and minimizes Kullback-Leibler divergence of the closed-loop description to the desired one. Practical exploitation of the fully probabilistic design control theory continues to be hindered by the computational complexities involved in numerically solving the associated stochastic dynamic programming problem. In particular very hard multivariate integration and an approximate interpolation of the involved multivariate functions. This paper proposes a new fully probabilistic contro algorithm that uses the adaptive critic methods to circumvent the need for explicitly evaluating the optimal value function, thereby dramatically reducing computational requirements. This is a main contribution of this short paper.

Full of Hot Air? Three Examinations of Climate Change in the American Political Information Environment

Climate change is thought to be one of the most pressing environmental problems facing humanity. However, due in part to failures in political communication and how the issue has been historically defined in American politics, discussions of climate change remain gridlocked and polarized. In this dissertation, I explore how climate change has been historically constructed as a political issue, how conflicts between climate advocates and skeptics have been communicated, and what effects polarization has had on political communication, particularly on the communication of climate change to skeptical audiences. I use a variety of methodological tools to consider these questions, including evolutionary frame analysis, which uses textual data to show how issues are framed and constructed over time; Kullback-Leibler divergence content analysis, which allows for comparison of advocate and skeptical framing over time; and experimental framing methods to test how audiences react to and process different presentations of climate change. I identify six major portrayals of climate change from 1988 to 2012, but find that no single construction of the issue has dominated the public discourse defining the problem. In addition, the construction of climate change may be associated with changes in public political sentiment, such as greater pessimism about climate action when the electorate becomes more conservative. As the issue of climate change has become more polarized in American politics, one proposed causal pathway for the observed polarization is that advocate and skeptic framing of climate change focuses on different facets of the issue and ignores rival arguments, a practice known as “talking past.” However, I find no evidence of increased talking past in 25 years of popular newsmedia reporting on the issue, suggesting both that talking past has not driven public polarization or that polarization is occurring in venues outside of the mainstream public discourse, such as blogs. To examine how polarization affects political communication on climate change, I test the cognitive processing of a variety of messages and sources that promote action against climate change among Republican individuals. Rather than identifying frames that are powerful enough to overcome polarization, I find that Republicans exhibit telltale signs of motivated skepticism on the issue, that is, they reject framing that runs counter to their party line and political identity. This result suggests that polarization constrains political communication on polarized issues, overshadowing traditional message and source effects of framing and increasing the difficulty communicators experience in reaching skeptical audiences.

Development of unsupervised learning methods with applications to life sciences data

Machine Learning makes computers capable of performing tasks typically requiring human intelligence. A domain where it is having a considerable impact is the life sciences, allowing to devise new biological analysis protocols, develop patients’ treatments efficiently and faster, and reduce healthcare costs. This Thesis work presents new Machine Learning methods and pipelines for the life sciences focusing on the unsupervised field. At a methodological level, two methods are presented. The first is an “Ab Initio Local Principal Path” and it is a revised and improved version of a pre-existing algorithm in the manifold learning realm. The second contribution is an improvement over the Import Vector Domain Description (one-class learning) through the Kullback-Leibler divergence. It hybridizes kernel methods to Deep Learning obtaining a scalable solution, an improved probabilistic model, and state-of-the-art performances. Both methods are tested through several experiments, with a central focus on their relevance in life sciences. Results show that they improve the performances achieved by their previous versions. At the applicative level, two pipelines are presented. The first one is for the analysis of RNA-Seq datasets, both transcriptomic and single-cell data, and is aimed at identifying genes that may be involved in biological processes (e.g., the transition of tissues from normal to cancer). In this project, an R package is released on CRAN to make the pipeline accessible to the bioinformatic Community through high-level APIs. The second pipeline is in the drug discovery domain and is useful for identifying druggable pockets, namely regions of a protein with a high probability of accepting a small molecule (a drug). Both these pipelines achieve remarkable results. Lastly, a detour application is developed to identify the strengths/limitations of the “Principal Path” algorithm by analyzing Convolutional Neural Networks induced vector spaces. This application is conducted in the music and visual arts domains.

Deep generative models for facial keypoints detection

A new area of machine learning research called deep learning, has moved machine learning closer to one of its original goals: artificial intelligence and general learning algorithm. The key idea is to pretrain models in completely unsupervised way and finally they can be fine-tuned for the task at hand using supervised learning. In this thesis, a general introduction to deep learning models and algorithms are given and these methods are applied to facial keypoints detection. The task is to predict the positions of 15 keypoints on grayscale face images. Each predicted keypoint is specified by an (x,y) real-valued pair in the space of pixel indices. In experiments, we pretrained deep belief networks (DBN) and finally performed a discriminative fine-tuning. We varied the depth and size of an architecture. We tested both deterministic and sampled hidden activations and the effect of additional unlabeled data on pretraining. The experimental results show that our model provides better results than publicly available benchmarks for the dataset.