Signed graphs are complex systems that represent trust relationships or preferences in various domains. Learning node representations in such graphs is crucial for many mining tasks. Although real-world signed relationships can be influenced by multiple latent factors, most existing methods often oversimplify the modeling of signed relationships by relying on social theories and treating them as simplistic factors. This limits their expressiveness and their ability to capture the diverse factors that shape these relationships. In this paper, we propose DINES, a novel method for learning disentangled node representations in signed directed graphs without social assumptions. We adopt a disentangled framework that separates each embedding into distinct factors, allowing for capturing multiple latent factors. We also explore lightweight graph convolutions that focus solely on sign and direction, without depending on social theories. Additionally, we propose a decoder that effectively classifies an edge's sign by considering correlations between the factors. To further enhance disentanglement, we jointly train a self-supervised factor discriminator with our encoder and decoder. Throughout extensive experiments on real-world signed directed graphs, we show that DINES effectively learns disentangled node representations, and significantly outperforms its competitors in the sign prediction task.

Mutual Information (MI) and Conditional Mutual Information (CMI) are multi-purpose tools from information theory that are able to naturally measure the statistical dependencies between random variables, thus they are usually of central interest in several statistical and machine learning tasks, such as conditional independence testing and representation learning. However, estimating CMI, or even MI, is infamously challenging due the intractable formulation. In this study, we introduce DINE (Diffeomorphic Information Neural Estimator)-a novel approach for estimating CMI of continuous random variables, inspired by the invariance of CMI over diffeomorphic maps. We show that the variables of interest can be replaced with appropriate surrogates that follow simpler distributions, allowing the CMI to be efficiently evaluated via analytical solutions. Additionally, we demonstrate the quality of the proposed estimator in comparison with state-of-the-arts in three important tasks, including estimating MI, CMI, as well as its application in conditional independence testing. The empirical evaluations show that DINE consistently outperforms competitors in all tasks and is able to adapt very well to complex and high-dimensional relationships.

If you're seeing something long and challenging, remember that having an alcoholic drink beforehand is asking for trouble. So be sure to do it. Decorate a room as if you're a set designer, letting your imagination run wild. As William Morris said, bin whatever isn't useful or beautiful. Study your favourite standup and learn their best joke off by heart. It's not just about making your friends laugh: comedy teaches confidence and communication. From Evan Hansen to Alexander Hamilton to Mary Poppins, find a character whose feelings mirror yours – then unleash that emotion. Improvisation isn't just some zany thing comedians do on telly. It's a philosophy, as Pippa Evans' recent book Improv Your Life shows. When you're thrown a curveball, deviate from your standard script.

The waive of labels in the target domain makes Unsupervised Domain Adaptation (UDA) an attractive technique in many real-world applications, though it also brings great challenges as model adaptation becomes harder without labeled target data. In this paper, we address this issue by seeking compensation from target domain prior knowledge, which is often (partially) available in practice, e.g., from human expertise. This leads to a novel yet practical setting where in addition to the training data, some prior knowledge about the target class distribution are available. We term the setting as Knowledge-guided Unsupervised Domain Adaptation (KUDA). In particular, we consider two specific types of prior knowledge about the class distribution in the target domain: Unary Bound that describes the lower and upper bounds of individual class probabilities, and Binary Relationship that describes the relations between two class probabilities. We propose a general rectification module that uses such prior knowledge to refine model generated pseudo labels. The module is formulated as a Zero-One Programming problem derived from the prior knowledge and a smooth regularizer. It can be easily plugged into self-training based UDA methods, and we combine it with two state-of-the-art methods, SHOT and DINE. Empirical results on four benchmarks confirm that the rectification module clearly improves the quality of pseudo labels, which in turn benefits the self-training stage. With the guidance from prior knowledge, the performances of both methods are substantially boosted. We expect our work to inspire further investigations in integrating prior knowledge in UDA. Code is available at https://github.com/tsun/KUDA.

To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (target). Despite impressive progress, prior methods always need to access the raw source data and develop data-dependent alignment approaches to recognize the target samples in a transductive learning manner, which may raise privacy concerns from source individuals. Several recent studies resort to an alternative solution by exploiting the well-trained white-box model from the source domain, yet, it may still leak the raw data through generative adversarial learning. This paper studies a practical and interesting setting for UDA, where only black-box source models (i.e., only network predictions are available) are provided during adaptation in the target domain. To solve this problem, we propose a new two-step knowledge adaptation framework called DIstill and fine-tuNE (DINE). Taking into consideration the target data structure, DINE first distills the knowledge from the source predictor to a customized target model, then fine-tunes the distilled model to further fit the target domain. Besides, neural networks are not required to be identical across domains in DINE, even allowing effective adaptation on a low-resource device. Empirical results on three UDA scenarios (i.e., single-source, multi-source, and partial-set) confirm that DINE achieves highly competitive performance compared to state-of-the-art data-dependent approaches. Code is available at \url{https://github.com/tim-learn/DINE/}.

Staff at the Mantra on Fort Street in Victoria take pride in their sumptuous lunch buffet. With different vegetarian and nonvegetarian curries offered every day, regular customers can look forward to a variety of dining options. Mantra on Fort Street also has a mechanical device that delivers drinks, cutlery, and other goodies to diners. It's a creation of GreenCo Robots, an Edmonton-based company headed by engineer Liang Yu. In a phone interview with the Straight, he said that about 30 of his firm's robots are in use across Canada.

Companies tapped more advanced bots to double check complex legal documents and contracts for irregularities at much higher speeds than remote workers. These types of efficiency gains are expected to drive growth in the software bot market for years, said Mihir Shukla, co-founder and chief executive of robotic process automation maker Automation Anywhere Inc., based in San Jose, Calif. "Most people recognize the need for automation," Mr. Shukla said at The Wall Street Journal's CIO Network Summit, held online Tuesday. Now there is an even greater appreciation at the board level, he said. The robotic process automation market is expected to grow by double digits through 2024, according to information-technology research and consulting firm Gartner Inc.

UiPath, a New York robotics automation company, on Friday said it had filed with the Securities and Exchange Commission for an initial public offering. The move comes not long after UiPath raised fresh capital from investors at a valuation of $35 billion, making the company one of the most valuable privately held tech businesses in the U.S., CNBC reported. The company, which plans to list on the New York Stock Exchange under the ticker symbol PATH, aims to raise $1 billion in the IPO, the SEC Form S-1 says. It has not detailed the number of shares it plans to offer or the estimated price range. In the fiscal year ended Jan.

The results are based on a survey of 1,000 full-time and part-time workers across a range of industries, including 223 employed in the tech sector, the firm said. The survey was conducted in April. Technology workers' fears could be a harbinger for the broader labor market in the aftermath of the pandemic, as tech company trends often spread across the corporate world over time, said KPMG tech-industry practice leader Tim Zanni. "Workers in the tech industry are closer to the technology and thus have a unique understanding, more so than other industries, of technology and its capabilities," said Mr. Zanni. He said workers at technology firms see emerging digital capabilities in early stages of development and are more likely to be thinking of the impact of these tools on their jobs.

Enjoy dinner drinks and a chance to meet… Leslie Nooteboom is Co-founder & Chief Product Officer of Humanising Autonomy, an AI tech startup with $6m funding, on a mission to improve human interaction with autonomous vehicles. Humanising Autonomy build human-centered tools that define how autonomous systems will interact with people. Their pedestrian intent prediction platform makes autonomous vehicles safer and more efficient in urban environments, with the aim of making cities more pleasant for every type of vulnerable road user. This dinner is perfect for… Startup founders and management level at startups working on AI, smart cities and/or sustainability solutions. This dinner is open to a limited number of service providers / advisors (unless a TableCrowd partner).