Abstract--Graph-based anomaly detection has been widely used for detecting malicious activities in real-world applications. Existing attempts to address this problem have thus far focused on structural feature engineering or learning in the binary classification regime. In this work, we propose to leverage graph contrastive learning and present the supervised GraphCAD model for contrasting abnormal nodes with normal ones in terms of their distances to the global context (e.g., the average of all nodes). To handle scenarios with scarce labels, we further enable GraphCAD as a self-supervised framework by designing a graph corrupting strategy for generating synthetic node labels. To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph. We conduct extensive experiments on four public datasets, demonstrating that 1) GraphCAD significantly and consistently outperforms various advanced baselines and 2) its self-supervised version without fine-tuning can achieve comparable performance with its fully supervised version. A real example of detecting the papers (red) that don't belong Technology, Tsinghua University, Beijing, China, 100084. Jian Song is with Zhipu.AI, Beijing, China. Kaibo Xu is with Mininglamp Technology, Beijing, China.

Analogical reasoning fundamentally involves exploiting redundancy in a given task, but there are various strategies for an intelligent agent to identify and exploit such redundancy, often resulting in very different levels of reasoning ability. We explore such variations of analogy in geometric reasoning task, namely the Raven's Progressive Matrices. We show how different analogical constructions used by the same basic imagery-based computational model -- varying only in how they "slice" a matrix problem into parts and search within/across these parts -- achieve very different test scores, substantially overlapping the range of human performance. Our findings suggest that the ability to build effective high-level analogical constructions is as important as competencies in low-level reasoning, which raises interesting questions about the extent to which building the "right" analogies contributes to individual differences in human reasoning and how intelligent agents might learn to build among different constructions in the first place.

The labels used to train machine learning (ML) models are of paramount importance. Typically for ML classification tasks, datasets contain hard labels, yet learning using soft labels has been shown to yield benefits for model generalization, robustness, and calibration. Earlier work found success in forming soft labels from multiple annotators' hard labels; however, this approach may not converge to the best labels and necessitates many annotators, which can be expensive and inefficient. We focus on efficiently eliciting soft labels from individual annotators. We collect and release a dataset of soft labels (which we call CIFAR-10S) over the CIFAR-10 test set via a crowdsourcing study (N=248). We demonstrate that learning with our labels achieves comparable model performance to prior approaches while requiring far fewer annotators -- albeit with significant temporal costs per elicitation. Our elicitation methodology therefore shows nuanced promise in enabling practitioners to enjoy the benefits of improved model performance and reliability with fewer annotators, and serves as a guide for future dataset curators on the benefits of leveraging richer information, such as categorical uncertainty, from individual annotators.

Quantum state tomography (QST), the task of estimating an unknown quantum state given measurement outcomes, is essential to building reliable quantum computing devices. Whereas computing the maximum-likelihood (ML) estimate corresponds to solving a finite-sum convex optimization problem, the objective function is not smooth nor Lipschitz, so most existing convex optimization methods lack sample complexity guarantees; moreover, both the sample size and dimension grow exponentially with the number of qubits in a QST experiment, so a desired algorithm should be highly scalable with respect to the dimension and sample size, just like stochastic gradient descent. In this paper, we propose a stochastic first-order algorithm that computes an $\varepsilon$-approximate ML estimate in $O( ( D \log D ) / \varepsilon ^ 2 )$ iterations with $O( D^3 )$ per-iteration time complexity, where $D$ denotes the dimension of the unknown quantum state and $\varepsilon$ denotes the optimization error. Our algorithm is an extension of Soft-Bayes to the quantum setup.

Buff your skills to keep your job and get a raise in ANY economic climate. This course BUNDLE keeps your skills sharp and your paycheque up! This masterclass is without a doubt the most comprehensive course available anywhere online. Even if you have zero experience, this course will take you from beginner to professional. Each certificate in this bundle is only awarded after you have completed every lecture of the course.

AI that analyzes data to help you make decisions is set to be an increasingly big part of business tools, and the systems that do that are getting smarter with a new approach to decision optimization that Microsoft is starting to make available. Machine learning is great at extracting patterns out of large amounts of data but not necessarily good at understanding those patterns, especially in terms of what causes them. A machine learning system might learn that people buy more ice cream in hot weather, but without a common sense understanding of the world, it's just as likely to suggest that if you want the weather to get warmer then you should buy more ice cream. Understanding why things happen helps humans make better decisions, like a doctor picking the best treatment or a business team looking at the results of AB testing to decide which price and packaging will sell more products. There are machine learning systems that deal with causality, but so far this has mostly been restricted to research that focuses on small-scale problems rather than practical, real-world systems because it's been hard to do. Deep learning, which is widely used for machine learning, needs a lot of training data, but humans can gather information and draw conclusions much more efficiently by asking questions, like a doctor asking about your symptoms, a teacher giving students a quiz, a financial advisor understanding whether a low risk or high risk investment is best for you, or a salesperson getting you to talk about what you need from a new car.

We are open to supporting 100% remote work anywhere within the U.S. ICFs Digital Modernization Division is a rapidly growing, entrepreneurial, technology department, seeking a React Node.JS Developer to support upcoming needs with our federal customers. Our Digital Modernization Division is an information technology and management consulting department that offers integrated, strategic solutions to its public and private-sector clients. ICF has the expertise, agility, and commitment to design, build, and operate high-performance IT engines to support all aspects of our clients business. Provides application software development services or technical support typically in a defined project. Develops program logic for new applications or analyzes and modifies logic in existing applications.

Want to know the easiest, simplest, and fastest way to write and deploy deep learning code? Welcome to Tensorflow 2.0: Deep Learning and Artificial Intelligence! Don't have time to read all this and just want to sign up for the course? Get 75% OFF HERE: https://bit.ly/3wzX8Ab Nearly 4 years after Tensorflow was released, the library has evolved to its official second version.

The course focuses on decision tree classifiers and random forest classifiers because most of the successful machine learning applications appear to be classification problems. Focusing on classification problems, the course uses the DecisionTreeClassifier and RandomForestClassifier methods of Python's Scikit-learn library. It prepares you for using decision trees and random forests to make predictions and understanding the predictive structure of data sets. This course is for people who want to use decision trees or random forests for prediction with Scikit-learn. This requires practical experience and the course facilitates you with Jupyter notebooks to review and practice the lessons' topics.

Charlie met with his co-worker Keith over lunch to plan a professional development day they were supposed to lead over April break, but Charlie kept losing the thread of the discussion. He couldn't stop thinking about who or what was maintaining backups of his old website. Keith sat opposite him with his compartmentalized lunchbox of raw ingredients; Keith only ever described the actions he performed on food as "meal prep," perhaps because cooking involved a willingness to adapt and surprise oneself. Charlie stabbed mindlessly at his corner-store Cobb salad, and by the second time he asked Keith to repeat something he'd just said, Keith's expression sank into sharp suspicion. "Charlie, come on," Keith said, but somewhat to Charlie's relief, Keith wasn't reading Charlie's mind and judging his salacious past.