Knowledge Graphs (KGs) have made a qualitative leap and effected a real revolution in knowledge representation. This is leveraged by the underlying structure of the KG which underpins a better comprehension, reasoning and interpreting of knowledge for both human and machine. Therefore, KGs continue to be used as a main driver to tackle a plethora of real-life problems in dissimilar domains. However, there is no consensus on a plausible and inclusive definition to domain KG. Further, in conjunction with several limitations and deficiencies, various domain KG construction approaches are far from perfection. This survey is the first to provide an inclusive definition to the notion of domain KG. Also, a comprehensive review of the state-of-the-art approaches drawn from academic works relevant to seven dissimilar domains of knowledge is provided. The scrutiny of the current approaches reveals a correlated array of limitations and deficiencies. The set of improvements to address the limitations of the current approaches are introduced followed by recommendations and opportunities for future research directions.

Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baseline to the different features used as input to the model. Being based on solid game-theoretic principles, Shapley values uniquely satisfy several desirable properties, which is why they are increasingly used to explain the predictions of possibly complex and highly non-linear machine learning models. Shapley values are well calibrated to a user's intuition when features are independent, but may lead to undesirable, counterintuitive explanations when the independence assumption is violated. In this paper, we propose a novel framework for computing Shapley values that generalizes recent work that aims to circumvent the independence assumption. By employing Pearl's do-calculus, we show how these 'causal' Shapley values can be derived for general causal graphs without sacrificing any of their desirable properties. Moreover, causal Shapley values enable us to separate the contribution of direct and indirect effects. We provide a practical implementation for computing causal Shapley values based on causal chain graphs when only partial information is available and illustrate their utility on a real-world example.

Unmanned aerial vehicles (UAVs) can be deployed to monitor very large areas without the need for network infrastructure. UAVs communicate with each other during flight and exchange information with each other. However, such communication poses security challenges due to its dynamic topology. To solve these challenges, the proposed method uses two phases to counter malicious UAV attacks. In the first phase, we applied a number of rules and principles to detect malicious UAVs. In this phase, we try to identify and remove malicious UAVs according to the behavior of UAVs in the network in order to prevent sending fake information to the investigating UAVs. In the second phase, a mobile agent based on a three-step negotiation process is used to eliminate malicious UAVs. In this way, we use mobile agents to inform our normal neighbor UAVs so that they do not listen to the data generated by the malicious UAVs. Therefore, the mobile agent of each UAV uses reliable neighbors through a three-step negotiation process so that they do not listen to the traffic generated by the malicious UAVs. The NS-3 simulator was used to demonstrate the efficiency of the SAUAV method. The proposed method is more efficient than CST-UAS, CS-AVN, HVCR, and BSUM-based methods in detection rate, false positive rate, false negative rate, packet delivery rate, and residual energy.

Machine learning applications can achieve significant performance gains by training on large volumes of data. In many applications, the training data is distributed across multiple data-owners, such as patient records at multiple medical institutions, and furthermore contains sensitive information, e.g., genetic information, financial transactions, and geolocation information. Such settings give rise to the following key problem that is the focus of this paper: How can multiple data-owners jointly train a machine learning model while keeping their individual datasets private from the other parties? More specifically, we consider a distributed learning scenario in which N data-owners (clients) wish to train a logistic regression model jointly without revealing information about their individual datasets to the other parties, even if up to T out of N clients collude. Our focus is on the semi-honest adversary setup, where the corrupted parties follow the protocol but may leak information in an attempt to learn the training dataset.

In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical multiple integration representation. Leveraging the fact that the integration domain and measure of typical kernels, e.g., Gaussian kernels, arc-cosine kernels, are fully symmetric, we introduce a deterministic fully symmetric interpolatory rule to efficiently compute its quadrature nodes and associated weights to approximate such typical kernels. This interpolatory rule is able to reduce the number of needed nodes while retaining a high approximation accuracy. Further, we randomize the above deterministic rule such that the proposed stochastic version can generate dimension-adaptive feature mappings for kernel approximation. Our stochastic rule has the nice statistical properties of unbiasedness and variance reduction with fast convergence rate. In addition, we elucidate the relationship between our deterministic/stochastic interpolatory rules and current quadrature rules for kernel approximation, including the sparse grids quadrature and stochastic spherical-radial rule, thereby unifying these methods under our framework. Experimental results on several benchmark datasets show that our fully symmetric interpolatory rule compares favorably with other representative random features based methods.

Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames in the presence of missing data. Specifically, DIVE introduces a missingness latent variable, disentangles the hidden video representations into static and dynamic appearance, pose, and missingness factors for each object. DIVE imputes each object's trajectory where data is missing. On a moving MNIST dataset with various missing scenarios, DIVE outperforms the state of the art baselines by a substantial margin. We also present comparisons for real-world MOTSChallenge pedestrian dataset, which demonstrates the practical value of our method in a more realistic setting. Our code and data can be found at https://github.com/Rose-STL-Lab/DIVE.

Many real-world planning domains involve diverse information sources, external entities, and variable-reliability agents, all of which may impact the confidence, risk, and sensitivity of plans. Humans reviewing a plan may lack context about these factors; however, this information is available during the domain generation, which means it can also be interwoven into the planner and its resulting plans. This paper presents a provenance-based approach to explaining automated plans. Our approach (1) extends the SHOP3 HTN planner to generate dependency information, (2) transforms the dependency information into an established PROV-O representation, and (3) uses graph propagation and TMS-inspired algorithms to support dynamic and counter-factual assessment of information flow, confidence, and support. We qualified our approach's explanatory scope with respect to explanation targets from the automated planning literature and the information analysis literature, and we demonstrate its ability to assess a plan's pertinence, sensitivity, risk, assumption support, diversity, and relative confidence.

Across machine learning (ML) sub-disciplines researchers make mathematical assumptions to facilitate proof-writing. While such assumptions are necessary for providing mathematical guarantees for how algorithms behave, they also necessarily limit the applicability of these algorithms to different problem settings. This practice is known--in fact, obvious-- and accepted in ML research. However, similar attention is not paid to the normative assumptions that ground this work. I argue such assumptions are equally as important, especially in areas of ML with clear social impact, such as fairness. This is because, similar to how mathematical assumptions constrain applicability, normative assumptions also limit algorithm applicability to certain problem domains. I show that, in existing papers published in top venues, once normative assumptions are clarified, it is often possible to get unclear or contradictory results. While the mathematical assumptions and results are sound, the implicit normative assumptions and accompanying normative results contraindicate using these methods in practical fairness applications.

Joaquin Oliver died in the 2018 Parkland shooting, but recently, he urged people to vote in the 2020 election. Oliver's parents used A.I. to have their dead son encourage people to vote for officials who support gun control, as an extension of the nonprofit they run, Change the Ref. Technologists 3D-printed Oliver's image and created a video of him speaking out against gun violence, which his parents could take to protests around the country. In the video, Oliver's likeness says "I mean, vote for me. Parkland victim Joaquin Oliver urged people to vote in a video that used artificial intelligence to imagine what he'd look like today. Oliver was killed in 2018 in the MSD high school shooting. The video of Oliver, titled "Unfinished Vote," used deepfake technology from Lightfarm Studios. For deepfakes--images and videos generated using A.I.--of celebrities, influencers, or politicians, or more typical public figures, the production team would usually have thousands of images and videos with which to train the A.I. But in the case of a teenager who was more famous after death than during life, the technologists didn't have much material to work with. Instead, they created a single image of his face using three different photographs. Still, the video is convincing enough. The uncanny valley effect comes after the fact, once you realize that the young man in the video who is speaking to you is not actually speaking. On Thursday, shortly before Halloween and in the wake of a much derided, viral tweet exposing her immense wealth and privilege, Kim Kardashian West reacted to Kanye West's surprise gift to her: a hologram of her dead father. In an Instagram post, Kardashian West wrote, "For my birthday, Kanye got me the most thoughtful gift of a lifetime.

The British grading algorithm fit a familiar pattern. Details of these algorithms are rarely made transparent to the public, even to so-called experts. These systems are routinely protected from scrutiny by claims of corporate secrecy and decisions by governments and institutions that limit access and transparency. What is known about them is often what's written by marketing departments and public relations representatives, presented to the public without evidence or verification. In Britain, government officials said the grading algorithm "was meant to make the system more fair," a line that makes good PR but gives us zero information about the suitability of the system for its task, nor even the definition of "fairness" they might be relying on.