Predicting the emergence of links in large evolving networks is a difficult task with many practical applications. Recently, the Science4cast competition has illustrated this challenge presenting a network of 64.000 AI concepts and asking the participants to predict which topics are going to be researched together in the future. In this paper, we present a solution to this problem based on a new family of deep learning approaches, namely Graph Neural Networks. The results of the challenge show that our solution is competitive even if we had to impose severe restrictions to obtain a computationally efficient and parsimonious model: ignoring the intrinsic dynamics of the graph and using only a small subset of the nodes surrounding a target link. Preliminary experiments presented in this paper suggest the model is learning two related, but different patterns: the absorption of a node by a sub-graph and union of more dense sub-graphs. The model seems to excel at recognizing the first type of pattern.

Beat is the fastest growing ride hailing app in Latin America and a part of the international FreeNow Group, the multi-service mobility joint venture backed by BMW Group and Daimler AG. One city at a time, we are on a mission to develop seamless mobility for a safe and sustainable urban life. We are proud to say we have launched Beat Tesla / Loonshot, the first and largest private all-electric vehicle service in Latin America. As an organization, we are committed to our drivers with ethical practices and a safe working environment. To our customers, we differentiate ourselves from other ride-hailing apps with our super user-friendly app and excellent customer service.

Language models built using semi-supervised machine learning on large corpora of natural language have very quickly enveloped the fields of natural language generation and understanding. In this paper we apply a zero-shot approach independently developed by a number of researchers now gaining recognition as a significant alternative to fine-tuning for evaluation on common sense tasks. A language model with relatively few parameters and training steps compared to a more recent language model (T5) can outperform it on a recent large data set (TimeDial), while displaying robustness in its performance across a similar class of language tasks. Surprisingly, this result is achieved by using a hyperparameter-free zero-shot method with the smaller model, compared to fine-tuning to the larger model. We argue that robustness of the smaller model ought to be understood in terms of compositionality, in a sense that we draw from recent literature on a class of similar models. We identify a practical cost for our method and model: high GPU-time for natural language evaluation. The zero-shot measurement technique that produces remarkable stability, both for ALBERT and other BERT variants, is an application of pseudo-log-likelihoods to masked language models for the relative measurement of probability for substitution alternatives in forced choice language tasks such as the Winograd Schema Challenge, Winogrande, and others. One contribution of this paper is to bring together a number of similar, but independent strands of research. We produce some absolute state-of-the-art results for common sense reasoning in binary choice tasks, performing better than any published result in the literature, including fine-tuned efforts. We show a remarkable consistency of the model's performance under adversarial settings, which we argue is best explained by the model's compositionality of representations.

This paper offers a comprehensive survey of recent developments in 3D object detection covering the full pipeline from input data, over data representation and feature extraction to the actual detection modules. We include basic concepts, focus our survey on a broad spectrum of different approaches arising in the last ten years and propose a systematization which offers a practical framework to compare those approaches on the methods level.

In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predictions. To prevent model stealing, existing defenses focus on detecting malicious queries, truncating, or distorting outputs, thus necessarily introducing a tradeoff between robustness and model utility for legitimate users. Instead, we propose to impede model extraction by requiring users to complete a proof-of-work before they can read the model's predictions. This deters attackers by greatly increasing (even up to 100x) the computational effort needed to leverage query access for model extraction. Since we calibrate the effort required to complete the proof-of-work to each query, this only introduces a slight overhead for regular users (up to 2x). To achieve this, our calibration applies tools from differential privacy to measure the information revealed by a query. Our method requires no modification of the victim model and can be applied by machine learning practitioners to guard their publicly exposed models against being easily stolen. Model extraction attacks (Tramèr et al., 2016; Jagielski et al., 2020; Zanella-Beguelin et al., 2021) are a threat to the confidentiality of machine learning (ML) models. They are also used as reconnaissance prior to mounting other attacks, for example, if an adversary wishes to disguise some spam message to get it past a target spam filter (Lowd & Meek, 2005), or generate adversarial examples (Biggio et al., 2013; Szegedy et al., 2014) using the extracted model (Papernot et al., 2017b). Furthermore, an adversary can extract a functionally similar model even without access to any real input training data (Krishna et al., 2020; Truong et al., 2021; Miura et al., 2021) while bypassing the long and expensive process of data procuring, cleaning, and preprocessing. This harms the interests of the model owner and infringes on their intellectual property. Defenses against model extraction can be categorized as active, passive, or reactive. Passive defenses try to detect an attack (Juuti et al., 2019) or truncate outputs (Tramèr et al., 2016), but these methods lower the quality of results for legitimate users. The main reactive defenses against model extraction attacks are watermarking (Jia et al., 2020b), dataset inference (Maini et al., 2021), and proof of learning (Jia et al., 2021). However, reactive approaches address model extraction post hoc, i.e., after the attack has been completed. We design a pro-active defense that prevents model stealing before it succeeds. Specifically, we aim to increase the computational cost of model extraction without lowering the quality of model outputs. Our method is based on the concept of proof-of-work (PoW) and its main steps are presented as a block diagram in Figure 1.

It is widely acknowledged that transparency of automated decision making is crucial for deployability of intelligent systems, and explaining the reasons why some decisions are "good" and some are not is a way to achieving this transparency. We consider two variants of decision making, where "good" decisions amount to alternatives (i) meeting "most" goals, and (ii) meeting "most preferred" goals. We then define, for each variant and notion of "goodness" (corresponding to a number of existing notions in the literature), explanations in two formats, for justifying the selection of an alternative to audiences with differing needs and competences: lean explanations, in terms of goals satisfied and, for some notions of "goodness", alternative decisions, and argumentative explanations, reflecting the decision process leading to the selection, while corresponding to the lean explanations. To define argumentative explanations, we use assumption-based argumentation (ABA), a well-known form of structured argumentation. Specifically, we define ABA frameworks such that "good" decisions are admissible ABA arguments and draw argumentative explanations from dispute trees sanctioning this admissibility. Finally, we instantiate our overall framework for explainable decision-making to accommodate connections between goals and decisions in terms of decision graphs incorporating defeasible and non-defeasible information.

A number of approaches have dealt with statistical assessment of self-similarity, and many of those are based on multiscale concepts. Most rely on certain distributional assumptions which are usually violated by real data traces, often characterized by large temporal or spatial mean level shifts, missing values or extreme observations. A novel, robust approach based on Theil-type weighted regression is proposed for estimating self-similarity in two-dimensional data (images). The method is compared to two traditional estimation techniques that use wavelet decompositions; ordinary least squares (OLS) and Abry-Veitch bias correcting estimator (AV). As an application, the suitability of the self-similarity estimate resulting from the the robust approach is illustrated as a predictive feature in the classification of digitized mammogram images as cancerous or non-cancerous. The diagnostic employed here is based on the properties of image backgrounds, which is typically an unused modality in breast cancer screening. Classification results show nearly 68% accuracy, varying slightly with the choice of wavelet basis, and the range of multiresolution levels used.

This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral, probabilistic, and deep metric learning. We first start with the definition of distance metric, Mahalanobis distance, and generalized Mahalanobis distance. In spectral methods, we start with methods using scatters of data, including the first spectral metric learning, relevant methods to Fisher discriminant analysis, Relevant Component Analysis (RCA), Discriminant Component Analysis (DCA), and the Fisher-HSIC method. Then, large-margin metric learning, imbalanced metric learning, locally linear metric adaptation, and adversarial metric learning are covered. We also explain several kernel spectral methods for metric learning in the feature space. We also introduce geometric metric learning methods on the Riemannian manifolds. In probabilistic methods, we start with collapsing classes in both input and feature spaces and then explain the neighborhood component analysis methods, Bayesian metric learning, information theoretic methods, and empirical risk minimization in metric learning. In deep learning methods, we first introduce reconstruction autoencoders and supervised loss functions for metric learning. Then, Siamese networks and its various loss functions, triplet mining, and triplet sampling are explained. Deep discriminant analysis methods, based on Fisher discriminant analysis, are also reviewed. Finally, we introduce multi-modal deep metric learning, geometric metric learning by neural networks, and few-shot metric learning.

This paper proposes a lightweight method to attract users and increase views of the video by presenting personalized artistic media -- i.e, static thumbnails and animated GIFs. This method analyzes lightweight thumbnail containers (LTC) using computational resources of the client device to recognize personalized events from full-length sports videos. In addition, instead of processing the entire video, small video segments are processed to generate artistic media. This makes the proposed approach more computationally efficient compared to the baseline approaches that create artistic media using the entire video. The proposed method retrieves and uses thumbnail containers and video segments, which reduces the required transmission bandwidth as well as the amount of locally stored data used during artistic media generation. When extensive experiments were conducted on the Nvidia Jetson TX2, the computational complexity of the proposed method was 3.57 times lower than that of the SoA method. In the qualitative assessment, GIFs generated using the proposed method received 1.02 higher overall ratings compared to the SoA method. To the best of our knowledge, this is the first technique that uses LTC to generate artistic media while providing lightweight and high-performance services even on resource-constrained devices.

The graph represents a network of 1,107 Twitter users whose tweets in the requested range contained "iiot bigdata", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Friday, 21 January 2022 at 11:47 UTC. The requested start date was Friday, 21 January 2022 at 01:01 UTC and the maximum number of tweets (going backward in time) was 7,500. The tweets in the network were tweeted over the 2-day, 8-hour, 23-minute period from Tuesday, 18 January 2022 at 16:30 UTC to Friday, 21 January 2022 at 00:53 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods.