MICROS Mixed Initiative ConveRsatiOnal Systems Workshop

MICROS@ECIR2021 aims at investigating and collecting novel ideas and contributions in the field of conversational systems . The first edition of the workshop on Mixed-Initiative ConveatiOnal Systems will have a particular focus on mixed-initiative conversationalsystems . The workshop will focus on the way users access online information, thus posing new challenges compared to traditional search and recommendation .…

Generalizing Adversarial Examples by AdaBelief Optimizer

AdaBelief iterative FastGradient Sign Method (AB-FGSM) proposed to generalize adversarial examples . The transfer rate is 7%-21% higher than latest attack methods . Compared with state-of-the-art attack methods, our proposedmethod can generate adversarial example effectively in the white-box setting,and the transfer rates are 7-21% more than latest methods .…

A fusion method for multi valued data

In this paper we propose an extension of the notion of deviation-basedaggregation function tailored to aggregate multidimensional data . Our objective is to improve the results obtained by other methods that try to select the best aggregation function for a particular set of data, such as penaltyfunctions .…

Covering a set of line segments with a few squares

We study three covering problems in the plane . The first is to decide whether agiven set of line segments can be covered by four unit-sized,axis-parallel squares . The second is to build a data structure on a trajectory to efficiently answer whether any query subtrajectory is coverable by up to three square squares.…

Re imagining Algorithmic Fairness in India and Beyond

Conventional algorithmic fairness is West-centric, as seen in sub-groups,values, and methods . In India, data is notalways reliable due to socio-economic factors, ML makers appear to followdouble standards, and AI evokes unquestioning aspiration . We contend that localising model fairness alone can be window dressing in India, where the distance between models and oppressed communities is large .…

A Simple Disaster Related Knowledge Base for Intelligent Agents

In this paper, we describe our efforts in establishing a simple knowledgebase by building a semantic network composed of concepts and word relationships in the context of disasters in the Philippines . We let experts from the fields of linguistics,disasters, and weather science evaluate our knowledge base and arrived at anagreeability rate of 64%.…

The emergence of visual semantics through communication games

In this work, we consider a signalling gamesetting in which a `sender’ agent must communicate the information about animage to a `receiver’ who must select the correct image from many distractors . We investigate the effect of the feature extractor’s weights and of the task being solved on the visual semantics learned by the models .…

Diverse Adversaries for Mitigating Bias in Training

Adversarial learning can learn fairer and less biased models of language than standard methods . However, current adversarial techniques only partiallymitigate model bias, added to which their training procedures are often unstable . In this paper, we propose a novel approach to adversarial learning based on the use of multiple diverse discriminators, whereby discriminators are encouraged to learn orthogonal hidden representations from one another .…

Multi Time Attention Networks for Irregularly Sampled Time Series

Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models . Multi-Time Attention Networks learn anembedding of continuous-time values and use an attention mechanism to produce afixed-length representation of a time series containing a variable number ofobservations .…

The Role of Cost in the Integration of Security Features in Integrated Circuits for Smart Cards

This essay investigates the role of cost in the development and production of secure integrated circuits . I also go on to examine potential ways of reducing the cost of production for secure chips . This essay ends with the conclusion that adding security features to chips meant to be used for secure applications is well worth it, because the potential damages and losses caused by such attacks are of comparable amounts to the costs of developing and producing a chip .…

Camera Invariant Feature Learning for Generalized Face Anti spoofing

There has been an increasing consensus in learning based face anti-spoofingthat the divergence in terms of camera models is causing a large domain gap in real application scenarios . We describe a framework that eliminates the influence of inherent variance from acquisition cameras at the feature level, leading to the generalized face spoofing detection model that could be highlyadaptive to different acquisition devices .…

Few Shot Website Fingerprinting Attack

This work introduces a novel data augmentation method for few-shot websitefingerprinting (WF) attack where only a handful of training samples per websiteare available for deep learning model optimization . We introduce amodel-agnostic, efficient, and Harmonious Data Augmentation (HDA) method that can improve deep WF attacking methods significantly .…

SpanEmo Casting Multi label Emotion Classification as Span prediction

Emotion recognition (ER) is an important task in Natural Language Processing (NLP) We propose a new model “SpanEmo” castingmulti-label emotion classification as span-prediction . We introduce a loss function focused on modelling multiple co-existing emotions inthe input sentence . Experiments performed on the SemEval2018 multi-labelemotion data over three language sets (i.e.,…

Facilitating Terminology Translation with Target Lemma Annotations

Most of the recent work on terminology integration in machine translation has assumed that terminology translations are given already inflected in forms that are suitable for the target language sentence . In day-to-day work of professional translators, however, it is seldom the case as translators work with bilingual glossaries where terms are given in their dictionary forms; finding the right target language form is part of the translation process .…

CHOLAN A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata

CHOLAN is a modular approach to target end-to-endentity linking (EL) over knowledge bases . It consists of a pipeline of twotransformer-based models integrated sequentially to accomplish the task . The empirical study was conducted on two well-known knowledge bases (i.e., Wikidata and Wikipedia) The empirical results suggest that CHOLan outperforms state-of-the-art approaches on standarddatasets such as CoNLL-AIDA, MSNBC, AQUAINT, ACE2004, and T-REx.…

Cyber Physical Energy Systems Security Threat Modeling Risk Assessment Resources Metrics and Case Studies

Cyber-physical systems (CPS) are interconnected architectures that employanalog, digital, and communication resources for their interaction with thephysical environment . CPS are the backbone of enterprise, industrial, and critical infrastructure . Attackstargeting cyber-physical energy systems (CPES) can have disastrous consequences . The security of CPES can be enhancedleveraging testbed capabilities to replicate power systems operation, discovervulnerabilities, develop security countermeasures, and evaluate grid operation under fault-induced or maliciously constructed scenarios .…

Identity aware Graph Neural Networks

Message passing Graph Neural Networks (GNNs) provide a powerful modelingframework for relational data . The expressive power of existing GNNsis upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test . Here we develop a class of message passing GNNs, named Identity-awareGraph Neural Networks .…

PAWLS PDF Annotation With Labels and Structure

PDF Annotation with Labels and Structure(PAWLS) is a new annotation tool designed specifically for the PDF documentformat . PAWLS is particularly suited for mixed-mode annotation and scenarios inwhich annotators require extended context to annotate accurately . The tool supports span-based textual annotation, N-ary relations and freeform,non-textual bounding boxes, all of which can be exported in convenient formats .…

Personalization Paradox in Behavior Change Apps Lessons from a Social Comparison Based Personalized App for Physical Activity

Social comparison-based features are widely used in social computing apps . Most existing apps are not grounded in social comparison theories . This paper is among the first to automatically personalize socialcomparison targets . In the context of an m-health app for physical activity, we use artificial intelligence (AI) techniques of multi-armed bandits.…

Applications of Deep Learning in Fundus Images A Review

The use of fundus images for the early screening of eye diseases is of great clinical importance . Deep learning is becoming more popular in related applications, such as lesion segmentation,biomarkers segmentation and disease diagnosis . We will also release and regularly update the state-of-the-art results and newly-released datasets at https://://github.com/nkicsl/Fundus…

Accumulating Risk Capital Through Investing in Cooperation

Recent work on promoting cooperation in multi-agent learning has resulted in many methods which successfully promote cooperation at the cost of becoming more vulnerable to exploitation by malicious actors . We show that this is anunavoidable trade-off and propose an objective which balances these concerns, Promoting both safety and long-term cooperation .…

Process Level Representation of Scientific Protocols with Interactive Annotation

Process Execution Graphs~(PEG) is a document-level representation of real-world wet lab biochemistry protocols . We manually annotate PEGs in a corpus of complex lab protocols with a novel interactive textual simulator . We use this data to developgraph-prediction models, finding them to be good at entity identification and local relation extraction, while our corpus facilitates further exploration of long-range relations .…

Emergent Communication under Competition

The literature in modern machine learning has only negative results for learning to communicate between competitive agents using standard RL . We use a modified sender-receiver game to study the spectrum ofpartially-competitive scenarios . We show communication can indeed emerge in a competitive setting .…

Cognitive Perspectives on Context based Decisions and Explanations

When human cognition is modeled in Philosophy and Cognitive Science, there is a pervasive idea that humans employ mental representations in order to navigatethe world and make predictions about outcomes of future actions . We show that the Contextual Importanceand Utility method for XAI share an overlap with the current new wave ofaction-oriented predictive representational structures, in ways that makes CIUa reliable tool for creating explanations that humans can relate to and trust .…

Black Feminist Musings on Algorithmic Oppression

This paper unapologetically reflects on the critical role that Black feminism can and should play in abolishing algorithmic oppression . Positioningalgorithmic oppression in the broader field of feminist science and technologystudies . I discuss what it means to call fordiversity as a solution to algorithmic violence, and I critique dialectics of the fairness, accountability, and transparency community .…

On maximum likelihood estimation in the all or nothing regime

We study the problem of estimating a rank-1 additive deformation of aGaussian tensor . The analysis is carried out in the sparse setting, where the underlying signal has a support that scales sublinearly with the total number of dimensions . We show that for Bernoulli distributed signals, the MLE undergoes an\emph{all-or-nothing} (AoN) phase transition, already established for theminimum mean-square-error estimator (MMSE) The result follows from two main technical points: (i) the connection established betweenthe MLE and the MMSE, using the first and second-moment methods in theconstrained signal space .…