Transfer Learning for Human & AI

In this paper, we revisit math word problems~(MWPs) from the cross-lingualand multilingual perspective . We construct our MWP solvers over pretrainedmultilingual language models using sequence-to-sequence model with copymechanism . We compare how the solvers perform in cross-language andmultilingual scenarios . Our experiments show that the MWPsolvers may not be transferred toa different language even if the target expressions have the same operator setand constants .…

Imitation Learning for Autonomous navigation (VOILA) is a new algorithm that can learn navigation policies from a single video demonstration collected from a physically different agent . VOILA successfully imitates the expert, but that it also learns navigation policies that can generalize to novel environments .…

In this paper, we use a model of large random network game to explore the conditions under which the Nash equilibrium (NE) of the game is affected by a perturbation . We use a phase transition phenomenon observed in finite rankdeformations of large .…

This paper introduces an efficient algorithm for the sequential positioning(or nested dissection) of two planar interfaces in an arbitrary polyhedron . Such that, after each truncation, the respectively remaining polyhedrons admit a prescribed volume . This task, among others, is frequently encountered in thenumerical simulation of three-phase flows when resorting to the geometricVolume-of-Fluid method .…

In this article, we consider the $c$-dispersion problem in a metric space$(X,d)$ We propose asimple polynomial time greedy algorithm that produces a $2c-factorapproximation result . The objective is to find a subset $S\subseteq P$ of size $k$ such that $cost_{c}(S)$ is maximized .…

Bitcoin is built on a blockchain, an immutable decentralised ledger thatallows entities (users) to exchange Bitcoins in a pseudonymous manner . Different heuristics exist to detect which addresses in a specific transaction belong to the same entity . In this paper, we analyse for the first time the Address Correspondence Network is characterised by a complex topology, signalled by a broad, skeweddegree distribution and a power-law component size distribution .…

Service provisioning mechanisms implemented across 5G infrastructures takebroadly into use of the network service chain concept . The IP MultimediaSubsystem (IMS) is a key infrastructure of 5G networks, that we characterize bothby a performance and an availability perspective . We perform a stochastic assessment of a softwarized IMS architecture where twomain stages stand out: i) a performance analysis, i.…

Automatic Essay Scoring (AES) is defined as the computer technology that evaluates and scores the written essays . In order to bridge this gap, we create a large corpus with several essays written by Brazilian high school students on an online platform .…

Current state estimation approaches are still highly vulnerable to false data injection (FDI) attacks . In this paper, we investigate the problem of the above three FDI attacks against dynamic power state estimation (DSE) In thisresearch, we propose two robust defense approaches .…

Data compression is widely used in contemporary column-oriented DBMSes . Pioneering systems have introduced compression to tackle the disk bandwidth bottleneck by trading CPU power for it . The main issue of this is a trade-off between the compression ratio and the decompression CPU cost .…

Poor medication adherence presents serious economic and health problems including compromised treatment effectiveness, medical complications, and billions of dollars in wasted medicine or procedures . There is an urgent need to leverage light, smart, and minimally obtrusive technology such assmartwatches to develop user tools to improve medication use and adherence .…

In this paper, we develop a learning-based approach for decentralizedsubmodular maximization . We focus on applications where robots are required to jointly select actions, e.g., to maximize team submodularobjectives with local communications only . We train the learning model by imitating an expert solution and implement the resulting model for decentralized action selection involving local observations and communications only.…

In 2019, The Centers for Medicare and Medicaid Services (CMS) launched an Artificial Intelligence (AI) Health Outcomes Challenge seeking solutions topredict risk in value-based care for incorporation into CMS Innovation Centerpayment and service delivery models . We propose a comprehensive modeling solution centered on a deeplearning framework for this data .…

The UIT-ViWikiQA is the first dataset forevaluating sentence extraction-based machine reading comprehension in theVietnamese language . The best machine model is XLM-R$_Large, which achieves an exact match (EM) score of85.97% and an F1-score of 88.77% on our dataset . We propose a conversional algorithm to create the dataset for sentence-based .…

In recent years, Internet users are reporting Adverse Drug Events (ADE) on social media, blogs and health forums . Because of the large volume of reports, pharmacovigilance is seeking to resort to NLP to monitor these outlets . Wepropose for the first time the use of the SpanBERT architecture for the task ofADE extraction: this new version of the popular BERT transformer showedimproved capabilities with multi-token text spans .…

QuatDE is anovel model with a dynamic mapping strategy to explicitly capture avariety of relational patterns . The mapping strategy dynamically selects the transitionvectors associated with each triplet, used to adjust the point position of theentity embedding vectors in the quaternion space via Hamilton product .…

Dark patterns have emerged as a set of methods to exploit cognitive biases . These patterns can have consequences that might range fromconvenience to global disasters . We present a case of a drug company and anelectronic medical record vendor who colluded to modify the medical record’s interface to induce clinicians to increase the prescription of extended-releaseopioids .…

A widely established set of unsupervised node embedding methods can beinterpreted as consisting of two distinctive steps: definition of asimilarity matrix based on graph of interest followed by explicit orimplicit factorization of such matrix . We propose a matrixfactorization method based on a loss function that generalizes that of theskip-gram model with negative sampling to arbitrary similarity matrices .…

Two operads are said to belong to the same Wilf class if they have the samegenerating series . If an operad has afinite Groebner basis, then the monomial basis of the operad forms anunambiguous context-free language . We discuss the deterministicgrammar which defines the language .…

In this paper, the role of secret key with finite rate is studied to enhancethe secrecy performance of the system when users are operating in interferencelimited scenarios . To address this problem, a 2-user Gaussian Z-IC with secrecyconstraint at the receiver is considered .…

Current deep learning techniques for style transfer would not be optimal for design support since their “one-shot” transfer does not fit exploratory design processes . To overcome this gap, we propose parametric transcription, which transcribes an end-to-end style transfer effect into parameters available in existing content editing tools .…

Hypersequent GV (HGV) is a modular and extensible corecalculus for functional programming with session types that enjoy deadlockfreedom, confluence, and strong normalisation . HGV exploits hyper-environments, which are collections of type environments, to ensure that structuralcongruence is type preserving . As a consequence we obtain a tight operationalcorrespondence between HGV and HCP, a hypersequent-based process-calculusinterpretation of classical linear logic .…

In [Lehrenfeld, Olshanskii. propose a new discretization method for PDEs on moving domains in thesetting of unfitted finite element methods, which is provably higher-orderaccurate in space and time . The keyingredient in the method, the transformation of the underlying mesh, is becomestime-dependent which gives rise to some technical issues .…

Understanding the properties of games played under computational constraints remains challenging . This paper presents a novel model for theprecomputation (preparing moves in advance) aspect of computationallyconstrained games . A fundamental trade-off is shown between randomness of play,and susceptibility to precomputing .…

A novel speaker diarization method called End-to-End-Neural-Diarization-vector clustering (EEND- vector clustering) was onlyevaluated so far on simulated 2-speaker meeting-like data . The proposed method combines advantages of bothframeworks, i.e. high performance and handling of overlapped speechbased on EEND, and robust handling of long recordings with an arbitrary number of speakers based on clustering-based approaches .…

Casson fluid flow model tightly coupled with variable coefficients ADR ($VADR$) equation . Casson viscositycoefficient is taken to be dependent upon solute mass concentration . This paper presents the stability and convergence analyses of the stabilized finiteelement solution . The proposed expressions of the stabilization parameters help in obtaining optimal order of convergences .…

Retinal Vessel Segmentation is important for diagnosis of various diseases . The research on retinal vessel segmentation focuses mainly on improvement of the segmentation model which is usually based on U-Net architecture . The success of the data augmentationrelies on successfully addressing the problem of input images .…

We give an algebraic characterisation of first-order logic with the neighbourrelation, on finite words . For this, we consider languages of finite words overalphabets with an involution on them . The natural algebras for such languagesare involution semigroups . To characterise the logic, we define a special kindof semidirect product of involution .product…

High-dimensional expanders generalize the notion of expander graphs to higher-dimensional simplicial complexes . Noelementary combinatorial construction with near-optimal expansion is known . Our construction achieves a spectral gap of $Omega ($Omega) for randomwalks on the $k$-dimensional faces, which is only quadratically worse than the optimal bound of $Theta (Theta) The construction is based on a high-dimensional variant of a tensor product .…

Aimsun, SymuVia, Vissim, SUMO are currently available for traffic impact assessment of new technologies such as truckplatooning . The same simulation studies can be performed in different simulation software . We designed a cross-platform architecture for simulating a truck platooning functionality using software from different software .…

In active Visual-SLAM, a robot relies on the information retrieved by its cameras to control its own movements for autonomous mapping of the environment . We obtain more accurate maps, with lower energy consumption, while maintaining the benefits of the active approach with respect to the baseline .…

Previous works have used the mean value as the estimate, motivated by channelhardening . However, this is associated with a performance loss in non-isotropicscattering environments . We propose two novel estimation methods that can be applied without downlink pilots . We compare the proposed methods with the state-of-the-art using the normalized mean-squared error and spectralefficiency (SE) The results suggest that the two proposed methods provide better SE than the state of theart when there is a low level of channel hardening, while the performance difference is relatively small with theuncorrelated channel model .…

Sketch-based conditions can effectively describe the geometry of faces, including contours of facial components, hairstructures, as well as salient edges (e.g., wrinkles) on face surfaces . However, existing disentangling methods are not optimized for human face editing, and cannotachieve fine control of facial details such as wrinkles .…

Faults in photovoltaic (PV) systems can seriously affect the efficiency, energy yield as well as the security of the entire PV plant . Fault diagnosis of PV arrays is indispensable for improving the reliability, efficiency, productivity and safety of PV powerstations .…

The computation of pointlikes can beinterpreted as the algebraic counterpart of the covering problem . This leadsto the notion of conelikes for the corresponding algebraic framework . We apply this framework to the Trotter-Weil hierarchy and both the full and the half levels of the $\text{FO}^2$ quantifier alternation hierarchy .…

We derive low-order, inf-sup stable and divergence-free finite element approximations for the Stokes problem using Worsey-Farin splits in threedimensions and Powell-Sabin splits in two dimensions . The velocity space simplyconsists of continuous, piecewise linear polynomials, where as the pressurespace is a subspace of piecewise constants with weak continuity properties atsingular edges (3D)…

In this paper, the authors derive several contiguous relations for terminating multivariatehypergeometric series . With these contiguous relations one can prove severalrecursion formulas of those series . This theoretical result allows to computeintegrals over products of Jacobi polynomials in a very efficient recursiveway .…

We consider two-variable first-order logic and its quantifieralternation hierarchies over both finite and infinite words . Deciding the presence or absence of such a pattern in agiven automaton is in $\mathbf{NL$ . This leads to algorithms for deciding the levels of the $\text{FO}^2$ quantifier alternationhierarchies .…

In this work, we propose a joint adaptive codebook construction and feedbackgeneration scheme in frequency division duplex (FDD) systems . Both unsupervisedand supervised deep learning techniques are used for this purpose . Subsequently, the feedback encoder can be offloaded to the mobile terminals to generate channel feedback there as efficiently as possible, without training effort at the terminals or corresponding transfer of training andcodebook data .…

We evolve PyDTNN, a framework for distributed parallel training of DeepNeural Networks, into an efficient inference tool for convolutionalneural networks . Ourexperiments evaluate both inference throughput (measured in processed images/s) and inference latency (i.e., time-to-response) when varying the level of thread parallelism and the processor powermodes .…

This paper introduces an efficient procedure to localize user-defined pointson the surface of deformable objects and track their positions in 3D space overtime . To cope with a deformable object’s infinite number of DOF, we propose adiscretized deformation field, which is estimated during runtime using amulti-step non-linear solver pipeline .…

We propose a novel approach to the problem of semantic heterogeneity . Conceptual, Language, Knowledge, and Data are uniformly dealt within each single layer, independently from the others . The proposed framework has been evaluated in various pilot case studies and in a number of industrial data integration problems .…

In this paper, we present a novel algorithm named synchronous integralQ-learning, which is based on synchronous policy iteration . The integral reinforcement is measured as an excitation signal to estimate the solution to the Hamilton-Jacobi-Bellmanequation . The proposed method is completely model-free, i.e.…

The most commonly used publication metrics for individual researchers are the total number of publications, and Hirsch’s $h$-index . Most other author-level measures in the literature share this cumulative property . By contrast, we aim to studynon-cumulative measures that answer the question “in terms of citation impact,what have you done lately?”…

Federated learning (FL) is a privacy-preserving machine learning method . It is proposed to allow training of models using data from many different clients, without these clients having to transfer all their data to a centralserver . FL models trained using the high-volume clients can perform similarly to a centrally-trained model, though there is much more noise in results than would typically be expected for acentrally-trained models .…

First study of automatic detoxification of Russian texts to combat offensive language . Such a kind of textual style transfer can be used,for instance, for processing toxic content in social media . The results show that the testedapproaches can be successfully used for detoxification, although there is room for improvement .…

Researchers analyzed communication behavior of 866 managers, out of which 111 left a large service company . Findings show managers who quit had lower closeness centrality and less engaged conversations . Researchers say managers who chose to quit tended to shift their communication behavior starting from 5 months before leaving, by increasing their degree, the complexity of their language, as well as their oscillations in betweenness centrality, and the number of “nudges” they need to send to peers before getting an answer .…

This paper focuses on how data centers can usetheir geographic load flexibility to reduce carbon emissions through cleverinteractions with electricity markets . Because electricity market clearingaccounts for congestion and power flow physics in the electric grid, the carbonemissions associated with electricity use varies between (potentiallygeographically close) locations .…

Two actively researched problem settings in matchings under preferences are popular matchings and the three-dimensional stable matching problem with cyclicpreferences . We investigate the connection between stability, popularity, and their strict variants, strong stability andstrong popularity in 3-dimensional instances . We also derive results on the complexity of these problems whenthe preferences are derived from master lists .…

An essential function of informationsystems should be the support of disclosure of this information . Without a set ofadequate information disclosure avenues an information system becomes worthless . We envision a computer supportedmechanism that allows for an easy and intuitive formulation of queries in allanguage that is as close to the user’s perception of the universe of discourseas possible.…