Network embedding (NE) approaches have emerged as a predominant technique to represent complex networks and have benefited numerous tasks. However, most NE approaches rely on a homophily assumption to learn embeddings with the guidance of supervisory signals, leaving the unsupervised heterophilous scenario relatively unexplored. This problem becomes especially relevant in fields where a scarcity of labels exists. Here, we formulate the unsupervised NE task as an r-ego network discrimination problem and develop the SELENE framework for learning on networks with homophily and heterophily. Specifically, we design a dual-channel feature embedding pipeline to discriminate r-ego networks using node attributes and structural information separately. We employ heterophily adapted self-supervised learning objective functions to optimise the framework to learn intrinsic node embeddings. We show that SELENE's components improve the quality of node embeddings, facilitating the discrimination of connected heterophilous nodes.

Extreme weather amplified by climate change is causing increasingly devastating impacts across the globe. The current use of physics-based numerical weather prediction (NWP) limits accuracy due to high computational cost and strict time-to-solution limits. We report that a data-driven deep learning Earth system emulator, FourCastNet, can predict global weather and generate medium-range forecasts five orders-of-magnitude faster than NWP while approaching state-of-the-art accuracy. FourCast-Net is optimized and scales efficiently on three supercomputing systems: Selene, Perlmutter, and JUWELS Booster up to 3,808 NVIDIA A100 GPUs, attaining 140.8 petaFLOPS in mixed precision (11.9%of peak at that scale). The time-to-solution for training FourCastNet measured on JUWELS Booster on 3,072GPUs is 67.4minutes, resulting in an 80,000times faster time-to-solution relative to state-of-the-art NWP, in inference. FourCastNet produces accurate instantaneous weather predictions for a week in advance, enables enormous ensembles that better capture weather extremes, and supports higher global forecast resolutions.

Nvidia Corp. and Google LLC have won top spots in the MLPerf Training machine learning competition, the organization that hosts the competition detailed today. MLPerf Training is run by the MLCommons Association, an industry group that develops open-source AI tools. Participants in the competition test how quickly they can train a series of neural networks to perform various computing tasks. The goal is to complete the training process as fast as possible and in accordance with certain technical criteria set forth by the MLCommons Association. This year's competition consisted of eight tests.

I bought Returnal, a video game from developer Housemarque, without knowing a thing about it. I knew from the trailer that it had something to do with escaping a time loop and there was some futuristic-looking technology and monsters or something. None of that mattered, because I wasn't buying it for the gameplay, I was buying it because of its protagonist, Selene. Selene is a fairly ordinary video game character in most respects: agile, capable, smart, facing a seemingly insurmountable challenge. It's unusual for the playable character to be a woman, but that's not what makes Selene special.

There is a new challenge workload on the horizon, one where few can afford to compete. But for those who can, it will spark a rethink in what is possible from even the most powerful traditional supercomputers. It might sound odd that it can be collected under the banner of language modeling since that invokes speech and text analysis and generation. But emerging workloads and research show how far this is from traditional natural language processing. Over the next several years, language models will likely become far more general purpose, encompassing an unimaginable range of problem types. Being able to have a world described through language and rendered as an image or video, or even asking text-based questions about the world with answers based on a system's understanding of our nuanced reality sounds like science fiction.

In under a month amid the global pandemic, a small team assembled the world's seventh-fastest computer. Today that mega-system, called Selene, communicates with its operators on Slack, has its own robot attendant and is driving AI forward in automotive, healthcare and natural-language processing. While many supercomputers tap exotic, proprietary designs that take months to commission, Selene is based on an open architecture NVIDIA shares with its customers. The Argonne National Laboratory, outside Chicago, is using a system based on Selene's DGX SuperPOD design to research ways to stop the coronavirus. The University of Florida will use the design to build the fastest AI computer in academia.

"Today that mega-system, called Selene, has its own robot attendant and is driving AI forward in automotive, healthcare and natural-language processing." Assembling supercomputers take years to build. It requires many service personnel working round the clock for many months to deliver a commission. But, beating all odds, NVIDIA claims to have built its supercomputer within three weeks. Not only did NVIDIA assemble a mammoth of a computer in a short time but also have broken records in the recently conducted MLPerf benchmark tests.

Our state of mind is based on experiences and what other people tell us. This may result in conflicting information, uncertainty, and alternative facts. We present a robot that models relativity of knowledge and perception within social interaction following principles of the theory of mind. We utilized vision and speech capabilities on a Pepper robot to build an interaction model that stores the interpretations of perceptions and conversations in combination with provenance on its sources. The robot learns directly from what people tell it, possibly in relation to its perception. We demonstrate how the robot's communication is driven by hunger to acquire more knowledge from and on people and objects, to resolve uncertainties and conflicts, and to share awareness of the per- ceived environment. Likewise, the robot can make reference to the world and its knowledge about the world and the encounters with people that yielded this knowledge.