Many of the world's most popular apps have dubious terms of service, and exploit private data to make money, according to a cybersecurity expert. He says that by allowing data to be monitored by'big tech' companies, they can decide what we see online, and we become'defined by what computer algorithms decide for us.' Below are Gaffney's three apps he would never use due to fears over privacy. Digital voice assistants such as Alexa are serious privacy risks, Gaffney says. The devices listen for'wake words' before operating but are listening to them all the time - and take snippets of your voice and process them in data centers far from your home. Gaffney says, 'I don't use them at all, but for those that do, I would not place them in the bathroom or bedroom.

In recent years, neural models have been repeatedly touted to exhibit state-of-the-art performance in recommendation. Nevertheless, multiple recent studies have revealed that the reported state-of-the-art results of many neural recommendation models cannot be reliably replicated. A primary reason is that existing evaluations are performed under various inconsistent protocols. Correspondingly, these replicability issues make it difficult to understand how much benefit we can actually gain from these neural models. It then becomes clear that a fair and comprehensive performance comparison between traditional and neural models is needed. Motivated by these issues, we perform a large-scale, systematic study to compare recent neural recommendation models against traditional ones in top-n recommendation from implicit data. We propose a set of evaluation strategies for measuring memorization performance, generalization performance, and subgroup-specific performance of recommendation models. We conduct extensive experiments with 13 popular recommendation models (including two neural models and 11 traditional ones as baselines) on nine commonly used datasets. Our experiments demonstrate that even with extensive hyper-parameter searches, neural models do not dominate traditional models in all aspects, e.g., they fare worse in terms of average HitRate. We further find that there are areas where neural models seem to outperform non-neural models, for example, in recommendation diversity and robustness between different subgroups of users and items. Our work illuminates the relative advantages and disadvantages of neural models in recommendation and is therefore an important step towards building better recommender systems.

Online inference is becoming a key service product for many businesses, deployed in cloud platforms to meet customer demands. Despite their revenue-generation capability, these services need to operate under tight Quality-of-Service (QoS) and cost budget constraints. This paper introduces KAIROS, a novel runtime framework that maximizes the query throughput while meeting QoS target and a cost budget. KAIROS designs and implements novel techniques to build a pool of heterogeneous compute hardware without online exploration overhead, and distribute inference queries optimally at runtime. Our evaluation using industry-grade deep learning (DL) models shows that KAIROS yields up to 2X the throughput of an optimal homogeneous solution, and outperforms state-of-the-art schemes by up to 70%, despite advantageous implementations of the competing schemes to ignore their exploration overhead.

Content creators compete for exposure on recommendation platforms, and such strategic behavior leads to a dynamic shift over the content distribution. However, how the creators' competition impacts user welfare and how the relevance-driven recommendation influences the dynamics in the long run are still largely unknown. This work provides theoretical insights into these research questions. We model the creators' competition under the assumptions that: 1) the platform employs an innocuous top-$K$ recommendation policy; 2) user decisions follow the Random Utility model; 3) content creators compete for user engagement and, without knowing their utility function in hindsight, apply arbitrary no-regret learning algorithms to update their strategies. We study the user welfare guarantee through the lens of Price of Anarchy and show that the fraction of user welfare loss due to creator competition is always upper bounded by a small constant depending on $K$ and randomness in user decisions; we also prove the tightness of this bound. Our result discloses an intrinsic merit of the myopic approach to the recommendation, i.e., relevance-driven matching performs reasonably well in the long run, as long as users' decisions involve randomness and the platform provides reasonably many alternatives to its users.

Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy. This paper introduces an end-to-end deep learning model, named RKGCN, which dynamically analyses each user's preferences and makes a recommendation of suitable items. It combines knowledge graphs on both the item side and user side to enrich their representations to maximize the utilization of the abundant information in knowledge graphs. RKGCN is able to offer more personalized and relevant recommendations in three different scenarios. The experimental results show the superior effectiveness of our model over 5 baseline models on three real-world datasets including movies, books, and music.

If you've been patiently waiting for a sale on the 5th-generation Echo Dot, now is the time to buy one. A handful of models are on sale. To start, you can get the basic model for $30 or 40 percent off. Moreover, all three colorways – charcoal, deep sea blue and glacier white – are part of the sale. Alternatively, the Echo Dot with Clock is also on sale.

To implement machine learning, it is essential to first determine an appropriate algorithm for the dataset. Different algorithms may produce a large number of different models with different hyperparameter configurations, and it usually takes a lot of time to run the model on a large dataset when the model is relatively complex. Therefore, how to predict the performance of a model on a dataset is an fundamental problem to be solved. This thesis designs a prediction system based on matrix factorization to predict the classification accuracy of a specific model on a particular dataset. In this thesis, we conduct a comprehensive empirical research on more than fifty datasets that we collected from the openml web site.

If you use Instagram, it's likely you've spotted a few strange changes to some of your friends' bios over the last few weeks. Thousands of users have added a pear emoji to the description on their profile - and there's a simple explanation as to why. The emoji is a new way for singletons to quietly indicate their relationship status. The idea is the brainchild of Pear - a dating concept that describes itself as'the world's biggest social experiment.' Here's everything you need to know, including what the emoji means and how you can use it in your profile.

In high performance systems it is sometimes hard to build very large graphs that are efficient both with respect to memory and compute. This paper proposes a data structure called Markov-chain-priority-queue (MCPrioQ), which is a lock-free sparse markov-chain that enables online and continuous learning with time-complexity of $O(1)$ for updates and $O(CDF^{-1}(t))$ inference. MCPrioQ is especially suitable for recommender-systems for lookups of $n$-items in descending probability order. The concurrent updates are achieved using hash-tables and atomic instructions and the lookups are achieved through a novel priority-queue which allows for approximately correct results even during concurrent updates. The approximatly correct and lock-free property is maintained by a read-copy-update scheme, but where the semantics have been slightly updated to allow for swap of elements rather than the traditional pop-insert scheme.

As some of you might know, I'm a runner. On occasion I review sports watches, and outside of work I'm a certified marathon coach. So when Engadget wanted to round up the best wireless workout headphones, I raised my hand. In addition to fit and battery life, I considered factors such as style; ease of use; the charging case; the strength of the Bluetooth connection; support for assistants such as Siri and Alexa; water resistance ratings; and audio features such as noise cancelation and ambient sound modes. You'll notice I don't have much if anything to say about sound quality. Engadget's resident expert Billy Steele has written plenty about the listening experience in his standalone reviews, which I've linked throughout, but for my purposes the differences were too subtle to make or break a purchasing decision. In the end, I never quite mastered some of the over-complicated controls, but at no point did an earbud fall out while I was exercising. I also never came close to running out of juice.