In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set changes remains unaddressed. In this paper, we present an algorithm that autonomously adapts to an action set whose size changes over time. To tackle this open problem, we break it into two problems that can be solved iteratively: inferring the underlying, unknown, structure in the space of actions and optimizing a policy that leverages this structure. We demonstrate the efficiency of this approach on large-scale real-world lifelong learning problems.

Contextual bandit algorithms have gained increasing popularity in recommender systems, because they can learn to adapt recommendations by making exploration-exploitation trade-off. Recommender systems equipped with traditional contextual bandit algorithms are usually trained with behavioral feedback (e.g., clicks) from users on items. The learning speed can be slow because behavioral feedback by nature does not carry sufficient information. As a result, extensive exploration has to be performed. To address the problem, we propose conversational recommendation in which the system occasionally asks questions to the user about her interest. We first generalize contextual bandit to leverage not only behavioral feedback (arm-level feedback), but also verbal feedback (users' interest on categories, topics, etc.). We then propose a new UCB- based algorithm, and theoretically prove that the new algorithm can indeed reduce the amount of exploration in learning. We also design several strategies for asking questions to further optimize the speed of learning. Experiments on synthetic data, Yelp data, and news recommendation data from Toutiao demonstrate the efficacy of the proposed algorithm.

Recently, matrix factorization-based recommendation methods have been criticized for the problem raised by the triangle inequality violation. Although several metric learning-based approaches have been proposed to overcome this issue, existing approaches typically project each user to a single point in the metric space, and thus do not suffice for properly modeling the intensity and the heterogeneity of user-item relationships in implicit feedback. In this paper, we propose TransCF to discover such latent user-item relationships embodied in implicit user-item interactions. Inspired by the translation mechanism popularized by knowledge graph embedding, we construct user-item specific translation vectors by employing the neighborhood information of users and items, and translate each user toward items according to the user's relationships with the items. Our proposed method outperforms several state-of-the-art methods for top-N recommendation on seven real-world data by up to 17% in terms of hit ratio. We also conduct extensive qualitative evaluations on the translation vectors learned by our proposed method to ascertain the benefit of adopting the translation mechanism for implicit feedback-based recommendations.

MOSCOW - Russia said on Monday it had added the popular dating app Tinder to a list of entities obliged to hand over user data and messages to law enforcement agencies on demand, including the main successor agency to the Soviet-era KGB. Roskomnadzor, Russia's telecoms and media regulator, said in a statement that Tinder had been added to its special register at the end of last month after providing the requisite information to allow itself to be added. The move, part of a wider Russian drive to regulate the internet, means that Tinder will be obliged to store users' metadata on servers inside Russia for at least six months as well as their text, audio or video messages. Russia's law enforcement agencies such as the FSB security service, which took over most of the KGB's functions, can require companies on the register to hand over data on demand. The Russian state's increased regulation of the internet has drawn criticism from some opposition politicians and sparked protests from campaigners who are concerned about what they say is creeping Chinese-style control of the online world.

During the last few decades, with the rise of Youtube, Amazon, Netflix and many other such web services, recommender systems have taken more and more place in our lives. From e-commerce (suggest to buyers articles that could interest them) to online advertisement (suggest to users the right contents, matching their preferences), recommender systems are today unavoidable in our daily online journeys. In a very general way, recommender systems are algorithms aimed at suggesting relevant items to users (items being movies to watch, text to read, products to buy or anything else depending on industries). Recommender systems are really critical in some industries as they can generate a huge amount of income when they are efficient or also be a way to stand out significantly from competitors. As a proof of the importance of recommender systems, we can mention that, a few years ago, Netflix organised a challenges (the "Netflix prize") where the goal was to produce a recommender system that performs better than its own algorithm with a prize of 1 million dollars to win.

After enjoying years of steady growth, your business suddenly sees your customer satisfaction scores sinking. When you investigate, you find that your customer support team is simply not keeping up with the volume of requests that they're receiving. Customers have to wait two or more days for a first response, and they're voicing their discontent in growing numbers on social media. You don't have enough money in the budget to hire and train more support staff, so the only realistic solution is to use AI and automation. Which use cases should you try to automate, and which tools should you use?

Latent factor models have achieved great success in personalized recommendations, but they are also notoriously difficult to explain. In this work, we integrate regression trees to guide the learning of latent factor models for recommendation, and use the learnt tree structure to explain the resulting latent factors. Specifically, we build regression trees on users and items respectively with user-generated reviews, and associate a latent profile to each node on the trees to represent users and items. With the growth of regression tree, the latent factors are gradually refined under the regularization imposed by the tree structure. As a result, we are able to track the creation of latent profiles by looking into the path of each factor on regression trees, which thus serves as an explanation for the resulting recommendations. Extensive experiments on two large collections of Amazon and Yelp reviews demonstrate the advantage of our model over several competitive baseline algorithms. Besides, our extensive user study also confirms the practical value of explainable recommendations generated by our model.

Artificial Intelligence is a big deal. Companies keep investing money in this technology to leverage their offer and serve the customers better. As usual, the industry giants are at on the frontline, researching ways on how to gain competitive advantage and come up with brand-new products and services. We have prepared an overview of the biggest names in the world of technology and their investment in AI. Google has a long history with AI and plans to evolve into the "AI-first world", as per the company's CEO Sundar Pichaim.

Cold-start problems are long-standing challenges for practical recommendations. Most existing recommendation algorithms rely on extensive observed data and are brittle to recommendation scenarios with few interactions. This paper addresses such problems using few-shot learning and meta learning. Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks. To accomplish this, we combine the scenario-specific learning with a model-agnostic sequential meta-learning and unify them into an integrated end-to-end framework, namely Scenario-specific Sequential Meta learner (or s^2 meta). By doing so, our meta-learner produces a generic initial model through aggregating contextual information from a variety of prediction tasks while effectively adapting to specific tasks by leveraging learning-to-learn knowledge. Extensive experiments on various real-world datasets demonstrate that our proposed model can achieve significant gains over the state-of-the-arts for cold-start problems in online recommendation. Deployment is at the Guess You Like session, the front page of the Mobile Taobao.

It's that time of year again when Apple gives folks a sneak peek at new features for the iPhone and iPad. The company does it every June at the Worldwide Developer's Conference (WWDC) a forum to hype up app makers on new tools they could use in their apps. We'll be in attendance Monday morning in San Jose, as usual, to keep you up on the latest on what's expected to be called iOS 13, the software that runs the iPhone, iPad and iPod Touch. The event starts at 10 a.m. PT and will be live-streamed at Apple.com.