Earbuds are nice, but a portable speaker shares music with friends. And now for Black Friday, many of our favorite music sharers are on sale. We found deals on many of the speakers we've tested for our various guides and reviews -- and most of those discounts are hitting the lowest prices of the year so far. One of the best deals is the JBL Flip 6, now 50 off. Further down the page you'll see deals we found on smart speakers and soundbars too. Most everything here has been pulled from our Bluetooth speaker buying guide, our smart speaker roundup and other buying advice articles. Here are the best speaker deals we could find for Black Friday.

When it comes to online dating, it may tempting to apply a beauty filter to bag yourself a date. But be warned, ladies – as this can make you appear less intelligent, according to a study. An online study involving more than 2,700 participants asked them to rate images of 462 individuals. These images consisted of original faces and their corresponding'beautified' versions. None of the participants were told that some images had a beauty filter applied, and none were given'before' and'after' pictures of the same individual.

With the development of the internet, recommending interesting products to users has become a highly valuable research topic for businesses. Recommendation systems play a crucial role in addressing this issue. To prevent the leakage of each user's (client's) private data, Federated Recommendation Systems (FedRec) have been proposed and widely used. However, extensive research has shown that FedRec suffers from security issues such as data privacy leakage, and it is challenging to train effective models with FedRec when each client only holds interaction information for a single user. To address these two problems, this paper proposes a new privacy-preserving recommendation system (PRSI), which includes a preprocessing module and two main phases. The preprocessing module employs split vectors and fake interaction items to protect clients' interaction information and recommendation results. The two main phases are: (1) the collection of interaction information and (2) the sending of recommendation results. In the interaction information collection phase, each client uses the preprocessing module and random communication methods (according to the designed interactive protocol) to protect their ID information and IP addresses. In the recommendation results sending phase, the central server uses the preprocessing module and triplets to distribute recommendation results to each client under secure conditions, following the designed interactive protocol. Finally, we conducted multiple sets of experiments to verify the security, accuracy, and communication cost of the proposed method.

The mobile gaming industry, particularly the free-to-play sector, has been around for more than a decade, yet it still experiences rapid growth. The concept of games-as-service requires game developers to pay much more attention to recommendations of content in their games. With recommender systems (RS), the inevitable problem of bias in the data comes hand in hand. A lot of research has been done on the case of bias in RS for online retail or services, but much less is available for the specific case of the game industry. Also, in previous works, various debiasing techniques were tested on explicit feedback datasets, while it is much more common in mobile gaming data to only have implicit feedback. This case study aims to identify and categorize potential bias within datasets specific to model-based recommendations in mobile games, review debiasing techniques in the existing literature, and assess their effectiveness on real-world data gathered through implicit feedback. The effectiveness of these methods is then evaluated based on their debiasing quality, data requirements, and computational demands.

The recent breakthrough of large language models (LLMs) in natural language processing has sparked exploration in recommendation systems, however, their limited domain-specific knowledge remains a critical bottleneck. Specifically, LLMs lack key pieces of information crucial for sequential recommendations, such as user behavior patterns. To address this critical gap, we propose IDLE-Adapter, a novel framework that integrates pre-trained ID embeddings, rich in domain-specific knowledge, into LLMs to improve recommendation accuracy. IDLE-Adapter acts as a bridge, transforming sparse user-item interaction data into dense, LLM-compatible representations through a Pre-trained ID Sequential Model, Dimensionality Alignment, Layer-wise Embedding Refinement, and Layer-wise Distribution Alignment. Furthermore, IDLE-Adapter demonstrates remarkable flexibility by seamlessly integrating ID embeddings from diverse ID-based sequential models and LLM architectures. Extensive experiments across various datasets demonstrate the superiority of IDLE-Adapter, achieving over 10\% and 20\% improvements in HitRate@5 and NDCG@5 metrics, respectively, compared to state-of-the-art methods.

The randomized power method has gained significant interest due to its simplicity and efficient handling of large-scale spectral analysis and recommendation tasks. As modern datasets contain sensitive private information, we need to give formal guarantees on the possible privacy leaks caused by this method. This paper focuses on enhancing privacy preserving variants of the method. We propose a strategy to reduce the variance of the noise introduced to achieve Differential Privacy (DP). We also adapt the method to a decentralized framework with a low computational and communication overhead, while preserving the accuracy. We leverage Secure Aggregation (a form of Multi-Party Computation) to allow the algorithm to perform computations using data distributed among multiple users or devices, without revealing individual data. We show that it is possible to use a noise scale in the decentralized setting that is similar to the one in the centralized setting. We improve upon existing convergence bounds for both the centralized and decentralized versions. The proposed method is especially relevant for decentralized applications such as distributed recommender systems, where privacy concerns are paramount.

We've tested scores of speakers over the years, and the best ones have made their way into three of our buying guides: soundbars, portable speakers and smart speakers. Right now Black Friday sales are bringing notable discounts to many of our top picks. So if you need a soundbar to make the dialogue on your TV clearer or want to take your music out on the porch once the weather warms back up, this is a good time to grab something new. Of course, Black Friday doesn't technically start until the day after Thanksgiving, but nearly every retailer and speaker brand has already pushed their holiday deals live. Some discounts are even hitting new all-time lows. As new sales appear and we find new notable discounts, we'll update this list. But for now, here are the best Black Friday deals on speakers we could find.

In the area of recommender systems, the vast majority of research efforts is spent on developing increasingly sophisticated recommendation models, also using increasingly more computational resources. Unfortunately, most of these research efforts target a very small set of application domains, mostly e-commerce and media recommendation. Furthermore, many of these models are never evaluated with users, let alone put into practice. The scientific, economic and societal value of much of these efforts by scholars therefore remains largely unclear. To achieve a stronger positive impact resulting from these efforts, we posit that we as a research community should more often address use cases where recommender systems contribute to societal good (RS4Good). In this opinion piece, we first discuss a number of examples where the use of recommender systems for problems of societal concern has been successfully explored in the literature. We then proceed by outlining a paradigmatic shift that is needed to conduct successful RS4Good research, where the key ingredients are interdisciplinary collaborations and longitudinal evaluation approaches with humans in the loop.

According to my imprecise calculations, there are approximately a zillion speakers on sale for Black Friday. So how can a mere human know which ones are worthy and which will make music sound like it's emanating from a tin can? We've done our part by testing and reviewing dozens of different options and putting the best of the lot into handy buying guides for smart speakers, soundbars and portable Bluetooth speakers. This is an even more rarefied list, made up of the speakers we recommend -- that are also seeing notable discounts. If you need a new way to listen to music, a soundbar to help suss out the dialogue on your TV or a smart speaker to fulfill your demands, read on for the best Black Friday speaker deals. Portable Bluetooth speakers make it easy for you to bring the music where plugs don't reach -- a picnic, the front stoop, an aimless wander along the North Country Trail.

If you've ever got an advert on social media for something you were just talking about, it might be more than an uncanny coincidence. Thanks to virtual assistants like Siri and Alexa, your smartphone isconstantly listening to everything you say. Worryingly, as long as you have consented to the terms and conditions, there is nothing illegal about using that data to bombard you with hyper-specific adverts. Luckily, experts at NordVPN have devised a simple test to work out if your phone is really eavesdropping on your conversations. By deliberately discussing random topics within earshot of your phone, you can see how long it takes for these subjects to appear in your social media feeds.