Graph Neural Networks (GNNs) have marked significant impact in traffic state prediction, social recommendation, knowledge-aware question answering and so on. As more and more users move towards cloud computing, it has become a critical issue to unleash the power of GNNs while protecting the privacy in cloud environments. Specifically, the training data and inference data for GNNs need to be protected from being stolen by external adversaries. Meanwhile, the financial cost of cloud computing is another primary concern for users. Therefore, although existing studies have proposed privacy-preserving techniques for GNNs in cloud environments, their additional computational and communication overhead remain relatively high, causing high financial costs that limit their widespread adoption among users. To protect GNN privacy while lowering the additional financial costs, we introduce Panther, a cost-effective privacy-preserving framework for GNN training and inference services in cloud environments. Technically, Panther leverages four-party computation to asynchronously executing the secure array access protocol, and randomly pads the neighbor information of GNN nodes. We prove that Panther can protect privacy for both training and inference of GNN models. Our evaluation shows that Panther reduces the training and inference time by an average of 75.28% and 82.80%, respectively, and communication overhead by an average of 52.61% and 50.26% compared with the state-of-the-art, which is estimated to save an average of 55.05% and 59.00% in financial costs (based on on-demand pricing model) for the GNN training and inference process on Google Cloud Platform.

The Dallas Cowboys had just won the Vince Lombardi Trophy, handing the Buffalo Bills their third straight loss in the Super Bowl. Bill Clinton was sworn into office as the 42nd president of the United States. And American music icon Prince became The Artist Formerly Known as Prince. It was also the last time a Canadian hockey team won the Stanley Cup. On Saturday night, the Edmonton Oilers hope to take the first step toward breaking that drought when they take on the Florida Panthers in Game 1 of the Stanley Cup Final.

Genetic pathways usually encode molecular mechanisms that can inform targeted interventions. It is often challenging for existing machine learning approaches to jointly model genetic pathways (higher-order features) and variants (atomic features), and present to clinicians interpretable models. In order to build more accurate and better interpretable machine learning models for genetic medicine, we introduce Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learning (PANTHER). PANTHER selects informative genetic pathways that directly encode molecular mechanisms. We apply genetically motivated constrained tensor factorization to group pathways in a way that reflects molecular mechanism interactions. We then train a softmax classifier for disease types using the identified pathway groups. We evaluated PANTHER against multiple state-of-the-art constrained tensor/matrix factorization models, as well as group guided and Bayesian hierarchical models. PANTHER outperforms all state-of-the-art comparison models significantly (p<0.05). Our experiments on large scale Next Generation Sequencing (NGS) and whole-genome genotyping datasets also demonstrated wide applicability of PANTHER. We performed feature analysis in predicting disease types, which suggested insights and benefits of the identified pathway groups.

At first it seemed like director Ryan Coogler was simply listening to cultural kismet when he tapped Kendrick Lamar to put together the companion album to Black Panther. Casting the decade's reigning monarch (butterfly) of complex blackness in popular music logically followed from assembling a royal procession of black actors (among whom even Angela Bassett can sashay in as the Wakandan queen mother and barely steal focus) and a palatial retinue of behind-the-camera black excellence to mount a redefinition of the decade's reining genre of popcorn entertainment, the superhero movie. From Good Kid, M.A.A.D. City onward, Lamar's always represented his own trinity of black superhero, supervillain, and mortal in one person, exiled in a world not of his making. Who else, then, but King Kendrick or, as he's more Afrocentrically dubbed himself, King Kunta, for this epic of imagined African kingship transcending an American cartoon mythos? Who else but Kung Fu Kenny for this action film meant to dropkick historical trauma with a kinetic pivot to utopian possibility?

And can do it all in high winds, and while carrying a maximum of 15 pounds. Its makers boast that it is ideal for pipeline inspection, and with the ability to travel almost 60 miles on the ground, as well as hopping over small obstacles, it's certainly nimble enough for some field work. Advanced Tactics first tested a version of the Panther in 2012, and last week released a video of the new, commercial model driving and flying as part of a presale promotion. The Panther is an interesting, novel drone design, but it's also a test case for Advanced Tactics far more interesting vehicle: the larger, human-carrying Black Knight Transformer. With a similar wheels-and-rotors configuration, the Transformer was floated in 2014 as a possible medical evacuation vehicle for the military.

Journeyman director Stephen Hopkins doesn't try to pep up the bland biopic formula with his Jesse Owens drama "Race," but he does deliver a reasonably stirring version of a story that bears retelling. Stephan James gives an engaging performance as Owens, who overcomes prejudice and intense national pressure to compete and win at the 1936 Olympic Games. The movie leans heavily on a simplistic heroes-and-villains narrative, but that's hard to fault too much when the main bad guy is, y'know, Adolf Hitler. Ultimately, "Race" is broad but effective, reminding viewers of an important moment in the history of American sports and patriotism -- which was also one more step down the long, seemingly unending road toward eliminating bigotry. Cult animator Bill Plympton has made one of his oddest and most entertaining feature films with the mockumentary "Hitler's Folly," which uses some of the Nazi leader's real artwork and early biographical details to imagine an alternate history where Hitler aimed to be a rival to Walt Disney as well as a genocidal dictator. While Hitler steers the Reich's resources into making one unwieldy epic, Disney responds by putting all of his studio's visionary technicians to work on the American war effort, employing animatronic robots to fool the enemy.