We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario. STAR-GCN employs a stack of GCN encoder-decoders combined with intermediate supervision to improve the final prediction performance. Unlike the graph convolutional matrix completion model with one-hot encoding node inputs, our STAR-GCN learns low-dimensional user and item latent factors as the input to restrain the model space complexity. Moreover, our STAR-GCN can produce node embeddings for new nodes by reconstructing masked input node embeddings, which essentially tackles the cold start problem. Furthermore, we discover a label leakage issue when training GCN-based models for link prediction tasks and propose a training strategy to avoid the issue. Empirical results on multiple rating prediction benchmarks demonstrate our model achieves state-of-the-art performance in four out of five real-world datasets and significant improvements in predicting ratings in the cold start scenario. The code implementation is available in https://github.com/jennyzhang0215/STAR-GCN.

It's never easy to predict the future, and the speakers of Data Science Salon New York have somewhat divergent views on how we might expect ML and AI to be applied to the field of Media and Entertainment in the next five to ten years. But there's one clear area of agreement: "We're going to continue to see the implementation (and improvement) of personalized recommendation algorithms that are based on person-level data." said Lauren Lombardo, Senior Data Scientist at Nielsen. "It will vastly improve the overall relevance of the content and advertisements served across premium video, and make content exploration much simpler and more enjoyable," suggests Chris Whitely, Senior Director, Applied Analytics at Comcast. But the recommendation engines of tomorrow will be even more robust. "We've barely scratched the surface of utilizing recommendation engines for generating new content," said Josh Miller, Director of Data Analytics at Samba.tv.

When the Amazon Prime Day deals roll into town in July, it's a no-brainer that the Amazon Echo Dot will get a big discount like it does every year. The thing is, it'll be nowhere near as good as this one - and it ends at 9am tomorrow. This is a UK-only deal, but we've rounded up the latest top deals in the US over on our Memorial Day sales page. UK readers, be sure to check out the Bank Holiday sales this weekend too. We're expecting Prime Day to bring the Echo Dot down to £29.99 as per usual, or £24.99 at the very best if Google aggressively price cuts the Google Home Mini as the search giant can't help but wind Amazon up any chance it gets with its line of rival smart speakers.

Playing with my Lego, as a child, I would build human-like figures. I would create a whole cast of goodies and baddies, who would invariably end up fighting. The goodies always spoke with a North American drawl, while the baddies spoke English with heavy foreign accents. The very few female characters in my games were either shrieking, hyper-feminine princesses who needed saving, or near-voiceless helpers who looked after the base and cared for the wounded heroes. My bedroom carpet was a showground for the stereotypes of the day.

The future of car traffic is self-propelled or at least much more automated than before. Keeping an eye on the many variables and possible situations requires exactly the qualities that a well-designed AI system brings with it. In this way, traffic runs more smoothly and, above all, more safely for all concerned. This is not even about your own vehicle. In China, for example, artificial intelligence is used to dynamically and automatically control traffic light circuits so that ambulances, police or fire brigades can arrive at the scene more quickly and provide assistance.

Just ask the creators of Alexa or Siri and they will confirm how important their dulcet tones are. Imagine the strain of having Amitabh Bachchan rasp out the weather report in the morning and answering sundry other queries throughout the day. For those still sceptical about the significance of a soothing timbre, there are the findings of a recent Unesco report that examines the implications of the charming feminine voice that almost all virtual assistants have been blessed with. The report noted that technology companies justify the use of obliging female voices by citing surveys that show that this is what consumers of both sexes prefer. What is seldom mentioned is that the same surveys show that people like the sound of a male voice when authoritative statements are being made and a female voice when help is being offered.

As a world class tourist destination, Spain is considered to have it all; from a rich vibrant culture, world heritage sights, and a culinary scene fit for any foodie, Spain has something for everyone. On the tech front, Spain is a rising star as its startup scene is becoming the country's most flourishing sector. However, let us rewind approximately 10 years to the global financial crisis that took the world by storm. Spain was heavily hit by the 2008 global financial crisis, when the housing market crashed, leaving half-finished projects scattered from the suburbs of Madrid to the shores of the Mediterranean coastline. The sense of revival in Spain is clearer than the waters off Barcelona's coastline.

Google Assistant turns three this year. Whether you love it or not, it's the AI for everyone. Google's intelligent little helper has been powering almost every other smartphone for the past few years, getting better and smarter each day. Despite its dominance on mobile devices, Google shows no signs of slowing down. Aggressive marketing, widespread device integration and new innovations show where Google is placing its eggs.

Artificial Intelligence (AI) is the new electricity of our times. That's what Chris Duffey, creative technologist says about this incredible technology revolutionizing industries the world over. His new book Superhuman Innovation showcases how AI will supercharge the workforce, the world of work, and can be harnessed to deliver powerful change. It is a practical guide to how AI and Machine Learning are impacting not only how businesses, brands, and agencies innovate, but also what they innovate: products, services and content. In this world of product and pricing parity, the delivery of superior service experience has become the new marketing, and the new real competitive edge. Superhuman Innovation discusses how AI will serve the superstar innovators of tomorrow by enabling them to see deeper insights and set sail for higher goals.

Typical graph embeddings may not capture type-specific bipartite graph features that arise in such areas as recommender systems, data visualization, and drug discovery. Machine learning methods utilized in these applications would be better served with specialized embedding techniques. We propose two embeddings for bipartite graphs that decompose edges into sets of indirect relationships between node neighborhoods. When sampling higher-order relationships, we reinforce similarities through algebraic distance on graphs. We also introduce ensemble embeddings to combine both into a "best of both worlds" embedding. The proposed methods are evaluated on link prediction and recommendation tasks and compared with other state-of-the-art embeddings. Our embeddings are found to perform better on recommendation tasks and equally competitive in link prediction. While being all highly beneficial in applications, we demonstrate that none of the existing state-of-the-art or our embeddings is clearly superior (in contrast to what is claimed in many papers), and discuss the trade offs present among them.