Many practical graph problems, such as knowledge graph construction and drug-drug interaction prediction, require to handle multi-relational graphs. However, handling real-world multi-relational graphs with Graph Neural Networks (GNNs) is often challenging due to their evolving nature, as new entities (nodes) can emerge over time. Moreover, newly emerged entities often have few links, which makes the learning even more difficult. Motivated by this challenge, we introduce a realistic problem of few-shot out-of-graph link prediction, where we not only predict the links between the seen and unseen nodes as in a conventional out-of-knowledge link prediction task but also between the unseen nodes, with only few edges per node. We tackle this problem with a novel transductive meta-learning framework which we refer to as Graph Extrapolation Networks (GEN). GEN meta-learns both the node embedding network for inductive inference (seen-to-unseen) and the link prediction network for transductive inference (unseen-to-unseen). For transductive link prediction, we further propose a stochastic embedding layer to model uncertainty in the link prediction between unseen entities. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction. The results show that our model significantly outperforms relevant baselines for out-of-graph link prediction tasks.

Word embeddings are usually derived from corpora containing text from many individuals, thus leading to general purpose representations rather than individually personalized representations. While personalized embeddings can be useful to improve language model performance and other language processing tasks, they can only be computed for people with a large amount of longitudinal data, which is not the case for new users. We propose a new form of personalized word embeddings that use demographic-specific word representations derived compositionally from full or partial demographic information for a user (i.e., gender, age, location, religion). We show that the resulting demographic-aware word representations outperform generic word representations on two tasks for English: language modeling and word associations. We further explore the trade-off between the number of available attributes and their relative effectiveness and discuss the ethical implications of using them.

Also a cross-disciplinary scientist, entrepreneur & author, recently relocated from Hong Kong to rural Seattle area. Eventually, Covid-19 will be beaten -- vaccines and therapies will be found and widely deployed. However, that doesn't mean the jobs that the pandemic has taken are coming back. Of course, some will return. For instance, restaurants will return to in-house dining and hire more waitstaff. But the rethinking and reorganization that Covid-19 has induced will have longer-term impacts.

The tragedy happened to the AirFrance 447 more than 10 years ago, in 2009. The flight took off in Rio de Janeiro and was planned to land in Paris. It suddenly disappeared in the middle of the Atlantic ocean without any warning. Immediately, rescuers reached the zone and what they found were just some wreckage and corpse. All 228 people onboard died in the crash.

Netflix is taking a swan dive into the Assassin's Creed video game franchise. The streaming TV giant will create a live-action TV series based on the Assassin's Creed series of video games, published by Ubisoft, the two companies announced Tuesday. Netflix may also eventually develop animated and anime series based on the hugely popular franchise, which chronicles a group of assassins' fight throughout history. "We're excited to partner with Ubisoft and bring to life the rich, multilayered storytelling that Assassin's Creed is beloved for," said Peter Friedlander, vice president of original series for Netflix, said in a statement. "From its breathtaking historical worlds and massive global appeal as one of the best selling video game franchises of all time, we are committed to carefully crafting epic and thrilling entertainment based on this distinct IP and provide a deeper dive for fans and our members around the world to enjoy."

When not building AI, enjoys mountain biking and a good book. Fiction through the effort of researchers and the stampede of scientific development has a tendency lately to become real. Artificial Intelligence is not one of those things. AI means a lot of different things to a lot of different people, so let's break it down. Think about dropping a Los Angeles alley cat into the Kruger National park in front of an elephant.

There are many more trees in the West African Sahara Desert than we thought, according to a recent study based on AI and satellite imagery and published in the journal Nature -- which found more than 1.8 billion trees in the Sahara Desert. Researchers have counted more than 1.8 billion trees and shrubs in the 501,933 square-mile (1.3 million square-kilometer) area -- in an area encompassing the western-most region of the Sahara Desert -- called the Sahel -- along with sub-humid zones of West Africa, reports The World Economic Forum. "We were very surprised to see that quite a few trees actually grow in the Sahara Desert, because up until now, most people thought that virtually none existed," said Professor Martin Brandt from the geosciences and natural resource management department of the University of Copenhagen and lead author of the recent study. "We counted hundreds of millions of trees in the desert alone. Doing so wouldn't have been possible without this technology," explained Brandt, according to a blog post on the University of Copenhagen's website.

The research report focuses on target groups of customers to help players to effectively market their products and achieve strong sales in the global Emotion Artificial Intelligence Market. Readers are provided with validated and revalidated market forecast figures such as CAGR, Emotion Artificial Intelligence market revenue, production, consumption, and market share. Our accurate market data equips players to plan powerful strategies ahead of time. The Emotion Artificial Intelligence report offers deep geographical analysis where key regional and country level markets are brought to light. The vendor landscape is also analysed in depth to reveal current and future market challenges and Emotion Artificial Intelligence business tactics adopted by leading companies to tackle them.

Tensor regression models, such as CP regression and Tucker regression, have many successful applications in neuroimaging analysis where the covariates are of ultrahigh dimensionality and possess complex spatial structures. The high-dimensional covariate arrays, also known as tensors, can be approximated by low-rank structures and fit into the generalized linear models. The resulting tensor regression achieves a significant reduction in dimensionality while remaining efficient in estimation and prediction. Brain functional connectivity is an essential measure of brain activity and has shown significant association with neurological disorders such as Alzheimer's disease. The symmetry nature of functional connectivity is a property that has not been explored in previous tensor regression models. In this work, we propose a sparse symmetric tensor regression that further reduces the number of free parameters and achieves superior performance over symmetrized and ordinary CP regression, under a variety of simulation settings. We apply the proposed method to a study of Alzheimer's disease (AD) and normal ageing from the Berkeley Aging Cohort Study (BACS) and detect two regions of interest that have been identified important to AD.

The path toward realizing the potential of seasonal forecasting and its socioeconomic benefits depends heavily on improving general circulation model based dynamical forecasting systems. To improve dynamical seasonal forecast, it is crucial to set up forecast benchmarks, and clarify forecast limitations posed by model initialization errors, formulation deficiencies, and internal climate variability. With huge cost in generating large forecast ensembles, and limited observations for forecast verification, the seasonal forecast benchmarking and diagnosing task proves challenging. In this study, we develop a probabilistic deep neural network model, drawing on a wealth of existing climate simulations to enhance seasonal forecast capability and forecast diagnosis. By leveraging complex physical relationships encoded in climate simulations, our probabilistic forecast model demonstrates favorable deterministic and probabilistic skill compared to state-of-the-art dynamical forecast systems in quasi-global seasonal forecast of precipitation and near-surface temperature. We apply this probabilistic forecast methodology to quantify the impacts of initialization errors and model formulation deficiencies in a dynamical seasonal forecasting system. We introduce the saliency analysis approach to efficiently identify the key predictors that influence seasonal variability. Furthermore, by explicitly modeling uncertainty using variational Bayes, we give a more definitive answer to how the El Nino/Southern Oscillation, the dominant mode of seasonal variability, modulates global seasonal predictability.