KPop Fandoms drive COVID 19 Public Health Messaging on Social Media

This report examines an unexpected but significant source of positive public health messaging during the COVID-19 pandemic . Analyses reveal theSouth Korean boyband BTS as the most significant driver of health discourse . Tweets from health agencies and prominent figures that mentioned K-pop generate111 times more of online response compared to tweets that did not .…

Fair Regression under Sample Selection Bias

All previous fair regressionresearch assumed training data and testing data are drawn from the samedistributions . This assumption is often violated in real world due to sample selection bias between training and testing . In this paper, wedevelop a framework for fair regression under sample selection .…

TranSalNet Visual saliency prediction using transformers

Convolutional neural networks (CNNs) have significantly advancedcomputational modeling for saliency prediction . But the inherent inductivebiases of convolutional architectures cause insufficient long-range contextualencoding capacity, which potentially makes a saliency model less humanlike . The proposed model achieves promising results in predicting saliency, and the new components make improvements, according to the paper .…

Representation of professions in entertainment media Insights into frequency and sentiment trends through computational text analysis

Media portrayal of culture, education, government, religion, and family affect function and evolution over time as people interpret and perceive theserepresentations and incorporate them into their beliefs and actions . In this work, we examine media representation ofprofessions and provide computational insights into their incidence, andsentiment expressed, in entertainment media content .…

Uniform Guarded Fragments

In this paper we prove that the uniform one-dimensional guarded fragment is a natural polyadic generalization of the guarded two-variable logic . We will also prove that . the satisfactioniability problem of uniform guarded fragment of uniform . fragment is NEXPTIME-complete .…

Toward a Wearable Biosensor Ecosystem on ROS 2 for Real time Human Robot Interaction Systems

The package standardizes biosensor HRIintegration, lowers the technical barrier of entry, and expands the biosensorecosystem into the robotics field . The wearable biosensor package is made publicly available on GitHub atÂhttps://://https://github.com/SMARTlab-Purdue/ros2-foxy-wearable-biosensors. We expect that standardization of this biosensors package for ROS2 will greatly simplify use and cross-collaboration across many disciplines.…

Chromatic Aberration Recovery on Arbitrary Images

Digital imaging sensor technology has continued to outpace development inoptical technology in modern imaging systems . The resulting quality lossattributable to lateral chromatic aberration is becoming increasinglysignificant as sensor resolution increases . The goals ofhigher-performance and lighter lens systems drive a recent need to find new ways to overcome resulting image quality limitations .…

Bounds for the Twin width of Graphs

Bonnet, Kim, Thomass\'{e, and Watrigant (2020) introduced the twin-width of a graph . We show that the twin width of an $n$-vertex graph is less than $(n+\sqrt{n\ln n}+\qrt {n}+2\lt n}$ asymptotically almost surely for any positive $varepsilon$ We also calculate the twinwidth of randomgraphs $G(n,p)$ with $p\leq c/n$ for a constant $c <1$ and $1$ to $2$ . …

A subexponential view of domains in session types

Linear logic (LL) has inspired the design of many computational systems,offering reasoning techniques built on top of its meta-theory . The subexponentials in LL have played an important role in concurrent systems since they can beinterpreted in different ways, including timed, spatial and even epistemicmodalities in distributed systems .…

Measure Twice Cut Once Quantifying Bias and Fairness in Deep Neural Networks

Bias in AI is more abstract and unintuitive forms of discrimination and can be more difficult to detect andmitigate . A clear gap exists in the current literature on evaluating therelative bias in the performance of multi-class classifiers . In this work, we propose two simple yet effective metrics, Combined Error Variance (CEV) andSymmetric Distance Error (SDE) to quantitatively evaluate the class-wise bias of two models in comparison to one another .…

A Framework for Aspectual Requirements Validation An Experimental Study

Aspect-Oriented Requirements Engineering (AORE) extends the existing software engineering approaches to cope with the issue of tangling andscattering resulted from crosscutting concerns . The proposed framework comprises a high-level and low-levelvalidation to implement on software requirements specification (SRS) Validation of requirements artefacts is an essential task in software development .…

Knowledge aware Coupled Graph Neural Network for Social Recommendation

Social recommendation task aims to predict users’ preferences over items with the incorporation of social connections among users . KCGN enables the high-order user- and item-wise relation encoding byexploiting the mutual information for global graph structure awareness . We further augment KCGN with the capability of capturing dynamicmulti-typed user-item interactive patterns .…

Towards Math Aware Automated Classification and Similarity Search of Scientific Publications Methods of Mathematical Content Representations

In this paper, we investigate mathematical content representations suitablefor the automated classification of and the similarity search in STEM documents . The methods are evaluated on asubset of arXiv.org papers with the Mathematics Subject Classification (MSC) as a reference classification and using the standard precision/recall/F1-measuremetrics .…

Nash Convergence of Mean Based Learning Algorithms in First Price Auctions

We consider repeated first price auctions where each bidder, having adeterministic type, learns to bid using a mean-based learning algorithm . We characterize the Nash convergence property of the bidding dynamics in two senses: (1) time-average: the fraction of rounds where bidders play aNash equilibrium approaches to 1 in the limit; (2) last-iterate: the mixedstrategy profile of bidder approaches to a Nash equilibrium in limit .…

Graph Meta Network for Multi Behavior Recommendation

Modern recommender systems often embed users and items into low-dimensionallatent representations, based on their observed interactions . Exploring multi-typed behavior patterns is of great importance torecommendation systems, yet is very challenging because of two aspects: i. The complex dependencies across different types of user-item interactions; ii)Diversity of such multi-behavior patterns may vary by users due to their personalized preference .…

Contextual Sentence Classification Detecting Sustainability Initiatives in Company Reports

We introduce the novel task of detecting sustainability initiatives incompany reports . Given a full report, the aim is to automatically identifymentions of practical activities that a company has performed in order totackle specific societal issues . As a single initiative can often be described over multiples sentences, new methods for identifying continuous sentence spans needs to be developed .…

A criterion for critical junctions in elastic plastic adhesive wear

We investigate elastic-plastic adhesive wear via a continuum variationalphase-field approach . The model seamlessly captures the transition fromperfectly brittle, over quasi-brittle to elastic-PLastic wear regimes . Simulation results highlight the existence of a critical condition that morphological features and materialductility need to satisfy for the adhesive junction to detach a wear debris .…

MAPA Multi Accelerator Pattern Allocation Policy for Multi Tenant GPU Servers

Multi-accelerator servers are increasingly being deployed in sharedmulti-tenant environments (such as in cloud data centers) in order to meet thedemands of large-scale compute-intensive workloads . We propose Multi-AcceleratorPattern Allocation (MAPA) a graph pattern mining approach . MAPA is able to improve theexecution time of multi-ACcelerator workloads and that MAPA can provide generalized benefits across various accelerator topologies.…

On the Optimal Memorization Power of ReLU Neural Networks

We study the memorization power of feedforward ReLU neural networks . We show that such networks can memorize any $N$ points that satisfy a mild separability assumption using $Omega(N/L) parameters . We also give a generalized construction for networks withdepth bounded by $1 \leq L (L) and $1) for memorizing $N samples .…

Isolation of connected graphs

For a connected $n-vertex graph $G$ and a set $F$ of graphs, let$iota(G,\mathcal{F)$ denote size of a smallest set $D$ of vertices . The bounds are sharp. We determine a set of six graphssuch that is not a copy of amember of the set of graphs $S$ of $G$.…

Sim2Ls FAIR simulation workflows and data

Sim2Ls allows developers to create and share end-to-end computational workflows with well-defined andverified inputs and outputs . The simulation ecosystem is available in nanoHUB, an openplatform that also provides publication services . We discuss best practices towards FAIR simulation workflows and associated data .…

IaaS Signature Change Detection with Performance Noise

We propose a novel framework to detect changes in the performance behavior of an IaaS service . A novel performancenoise model is proposed to accurately identify performance noise . A set of experiments based on real-world datasets is carried out to evaluate the effectiveness of the proposed framework .…

No Press Diplomacy from Scratch

Prior AI successes in complex games have largely focused on settings with atmost hundreds of actions at each decision point . In contrast, Diplomacy is agame with more than 10^20 possible actions per turn . Previous attempts to address games with large branching factors, such as Diplomacy, StarCraft, andDota, used human data to bootstrap the policy or used handcrafted rewardshaping.…

Visibility Reasoning for Concurrent Snapshot Algorithms

Visibility relations have been proposed by Henzinger et al. as an abstraction for proving linearizability of concurrent algorithms . This is in contrast to the customary approach based onexhibiting the algorithm’s linearization points . In this paper we applyvisibility relations to develop modular proofs for three elegant concurrentsnapshot algorithms of Jayanti .…

From the Head or the Heart An Experimental Design on the Impact of Explanation on Cognitive and Affective Trust

Automated vehicles (AVs) are social robots that can potentially benefit oursociety . According to the existing literature, AV explanations can promotepassengers’ trust by reducing the uncertainty associated with the AV’s reasoning and actions . Yet, the literature on AV explanations and trust has failed to consider how the type of trust – cognitive versus affective – might alter this relationship .…

Spike inspired Rank Coding for Fast and Accurate Recurrent Neural Networks

Biological spiking neural networks (SNNs) can temporally encode information in their outputs . Rank coding inspired by SNNs can also be applied to conventional ANNs such as LSTMs . In our RC for ANNs, we apply backpropagation through time using the standard real-valued activations, but only from a strategically early timestep of each sequential input example, decided by a threshold-crossing event .…

Learning Canonical Embedding for Non rigid Shape Matching

This paper provides a novel framework that learns canonical embeddings for non-rigid shape matching . In contrast to prior work in this direction, ourframework is trained end-to-end and thus avoids instabilities and constraints associated with the commonly-used Laplace-Beltrami basis or sequential optimization schemes .…

Federated Learning from Small Datasets

Federated learning allows multiple parties to collaboratively train a joint model without sharing local data . We propose a novel approach that intertwines model aggregations with permutations of local models . This enables training on extremely small localdatasets, such as patient data across hospitals, while retaining the trainingefficiency and privacy benefits of federated learning .…

Designing Composites with Target Effective Young s Modulus using Reinforcement Learning

Advances in additive manufacturing have enabled design and fabrication of materials and structures not previously realizable . Reinforcement learning(RL)-based framework for the design of composite structures avoids the need for user-selected training data . For a 5-times$ 5 composite design space, the model can be trained using 2.78% of the total design space consists of $2^{25$ design possibilities .…

On the Complexity of Inductively Learning Guarded Rules

We investigate the computational complexity of mining guarded clauses through the framework of inductive logic programming (ILP) Weshow that learning guarded clauses is NP-complete and thus one step below the task of learning Horn clauses on the polynomialhierarchy . Motivated by practical applications on large datasets we identify anatural tractable fragment of the problem .…