The other day I spent 10 minutes hurling verbal abuse at Siri. Cringing as I spoke, I said into my phone: "Siri, you're ugly." I said, "Siri, you're fat." She replied, "It must be all the chocolate." I felt mortified for both of us.

Knowledge graphs capture structured information and relations between a set of entities or items. As such knowledge graphs represent an attractive source of information that could help improve recommender systems. However, existing approaches in this domain rely on manual feature engineering and do not allow for an end-to-end training. Here we propose Knowledge-aware Graph Neural Networks with Label Smoothness regularization (KGNN-LS) to provide better recommendations. Conceptually, our approach computes user-specific item embeddings by first applying a trainable function that identifies important knowledge graph relationships for a given user. This way we transform the knowledge graph into a user-specific weighted graph and then apply a graph neural network to compute personalized item embeddings. To provide better inductive bias, we rely on label smoothness assumption, which posits that adjacent items in the knowledge graph are likely to have similar user relevance labels/scores. Label smoothness provides regularization over the edge weights and we prove that it is equivalent to a label propagation scheme on a graph. We also develop an efficient implementation that shows strong scalability with respect to the knowledge graph size. Experiments on four datasets show that our method outperforms state of the art baselines. KGNN-LS also achieves strong performance in cold-start scenarios where user-item interactions are sparse.

How to ensure human autonomy over our computational "screens, scenes, and unseens." Digital assistants such as Alexa and Siri and Google Assistant can be quite helpful -- but their actual allegiance is to Amazon and Apple and Google, not to the ordinary people who use them. By introducing AI-based digital agents that truly represent and advocate for us as individuals, rather than corporate or government institutions, we can make the Web a more trustworthy and accountable place. In the 2004 film "I Robot," Will Smith's character, the enigmatic Detective Del Spooner, harbors an animosity toward the humanoid-like robots operating in his society. Over the course of the film we learn why.

Recently, deep learning models play more and more important roles in contents recommender systems. However, although the performance of recommendations is greatly improved, the "Matthew effect" becomes increasingly evident. While the head contents get more and more popular, many competitive long-tail contents are difficult to achieve timely exposure because of lacking behavior features. This issue has badly impacted the quality and diversity of recommendations. To solve this problem, look-alike algorithm is a good choice to extend audience for high quality long-tail contents. But the traditional look-alike models which widely used in online advertising are not suitable for recommender systems because of the strict requirement of both real-time and effectiveness. This paper introduces a real-time attention based look-alike model (RALM) for recommender systems, which tackles the challenge of conflict between real-time and effectiveness. RALM realizes real-time look-alike audience extension benefiting from seeds-to-user similarity prediction and improves the effectiveness through optimizing user representation learning and look-alike learning modeling. For user representation learning, we propose a novel neural network structure named attention merge layer to replace the concatenation layer, which significantly improves the expressive ability of multi-fields feature learning. On the other hand, considering the various members of seeds, we design global attention unit and local attention unit to learn robust and adaptive seeds representation with respect to a certain target user. At last, we introduce seeds clustering mechanism which not only reduces the time complexity of attention units prediction but also minimizes the loss of seeds information at the same time. According to our experiments, RALM shows superior effectiveness and performance than popular look-alike models.

Science fiction is quickly becoming everyday reality. Chatbots, robots, digital assistants, automated vehicles, virtual assistants, and much more... are the products of artificial intelligence (AI), which is already transforming entire industries. An infographic by TechJury, provider of one-step tech guides and product reviews, provides a detailed overview of AI. The infographic begins with a timeline of AI, starting in the mid-20th century with the "father of theoretical computer science and artificial intelligence," Alan Turing, who developed the "Turing test" for determining what qualifies as artificial intelligence. The infographic goes on to outline various classifications of AI, provides examples of AI technology, highlights statistics about the AI market, and lists the companies and countries at the forefront of the AI race.

We focus on the problem of streaming recommender system and explore novel collaborative filtering algorithms to handle the data dynamicity and complexity in a streaming manner. Although deep neural networks have demonstrated the effectiveness of recommendation tasks, it is lack of explorations on integrating probabilistic models and deep architectures under streaming recommendation settings. Conjoining the complementary advantages of probabilistic models and deep neural networks could enhance both model effectiveness and the understanding of inference uncertainties. To bridge the gap, in this paper, we propose a Coupled Variational Recurrent Collaborative Filtering (CVRCF) framework based on the idea of Deep Bayesian Learning to handle the streaming recommendation problem. The framework jointly combines stochastic processes and deep factorization models under a Bayesian paradigm to model the generation and evolution of users' preferences and items' popularities. To ensure efficient optimization and streaming update, we further propose a sequential variational inference algorithm based on a cross variational recurrent neural network structure. Experimental results on three benchmark datasets demonstrate that the proposed framework performs favorably against the state-of-the-art methods in terms of both temporal dependency modeling and predictive accuracy. The learned latent variables also provide visualized interpretations for the evolution of temporal dynamics.

Joel Kontinen "Yoshua Bengio is one of the pioneering developers of artificial intelligence and winner of computing's'Nobel prize'. His optimism about machines doesn't extend to humanity. "OVER the past decade, machine intelligence has vastly improved. That is in large part due to deep learning, a technique that gives computers the ability to teach themselves. It underpins everything from world-beating chess and Go algorithms to digital voice assistants like Amazon's Alexa and Apple's Siri."

Over a decade ago, I was sitting in a college math physics course and my professor spelt out an idea that kind of blew my mind. I think it isn't a stretch to say that this is one of the most widely applicable mathematical discoveries, with applications ranging from optics to quantum physics, radio astronomy, MP3 and JPEG compression, X-ray crystallography, voice recognition, and PET or MRI scans. This mathematical tool--named the Fourier transform, after 18th-century French physicist and mathematician Joseph Fourier--was even used by James Watson and Francis Crick to decode the double helix structure of DNA from the X-ray patterns produced by Rosalind Franklin. You probably use a descendant of Fourier's idea every day, whether you're playing an MP3, viewing an image on the web, asking Siri a question, or tuning in to a radio station. In addition to his work in theoretical physics and math, he was also the first to discover the greenhouse effect.)

Collaborative filtering is widely used in modern recommender systems. Recent research shows that variational autoencoders (VAEs) yield state-of-the-art performance by integrating flexible representations from deep neural networks into latent variable models, mitigating limitations of traditional linear factor models. VAEs are typically trained by maximizing the likelihood (MLE) of users interacting with ground-truth items. While simple and often effective, MLE-based training does not directly maximize the recommendation-quality metrics one typically cares about, such as top-N ranking. In this paper we investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to directly optimize the non-differentiable quality metrics of interest. Specifically, we train a critic network to approximate ranking-based metrics, and then update the actor network (represented here by a VAE) to directly optimize against the learned metrics. In contrast to traditional learning-to-rank methods that require to re-run the optimization procedure for new lists, our critic-based method amortizes the scoring process with a neural network, and can directly provide the (approximate) ranking scores for new lists. Empirically, we show that the proposed methods outperform several state-of-the-art baselines, including recently-proposed deep learning approaches, on three large-scale real-world datasets. The code to reproduce the experimental results and figure plots is on Github: https://github.com/samlobel/RaCT_CF

Regardless of which piece of visual media or literature first instilled thoughts of artificial intelligence in our minds, it had quite the effect on us. Despite AI being very much a part of our current society, many of us don't realize it's here. Instead we're fixed on dystopian futures and malevolent machines. In reality, AI is disrupting dozens of sectors. From healthcare and transportation to fintech and telecommunications -- more than 154,000 AI patents have been filed since 2010 alone.