Check In, released in Apple's iOS 17 in 2023, is a messaging and location-tracking service that allows users to notify contacts when they have arrived at a destination. However, the feature makes suggestions on who users should alert and people have been left baffled by the recommendations. Users have shared these bizarre experiences on social media, with one woman saying she received a prompt to alert her deceased mother and another was sent a notification with her ex-husband's name - they divorced four years ago. A TikToker recently shared a video about the feature after repeatedly being prompted to check in with his boss. Apple released Check In last year, but users have reported only seeing the Siri suggestions over the last few months.

Neural Information Processing Systems http://nips.cc/

Low-rank matrix approximation (LRMA) methods have achieved excellent accuracy among today's collaborative filtering (CF) methods. In existing LRMA methods, the rank of user/item feature matrices is typically fixed, i.e., the same rank is adopted to describe all users/items. However, our studies show that submatrices with different ranks could coexist in the same user-item rating matrix, so that approximations with fixed ranks cannot perfectly describe the internal structures of the rating matrix, therefore leading to inferior recommendation accuracy. In this paper, a mixture-rank matrix approximation (MRMA) method is proposed, in which user-item ratings can be characterized by a mixture of LRMA models with different ranks. Meanwhile, a learning algorithm capitalizing on iterated condition modes is proposed to tackle the non-convex optimization problem pertaining to MRMA. Experimental studies on MovieLens and Netflix datasets demonstrate that MRMA can outperform six state-of-the-art LRMA-based CF methods in terms of recommendation accuracy.

Lifelong user behavior sequences, comprising up to tens of thousands of history behaviors, are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a few relevant behaviors are first searched from the original long sequences via an attention mechanism in the first stage and then aggregated with the target item to construct a discriminative representation for prediction in the second stage. In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes. Initial attempts to address this issue using linear projections -- a technique borrowed from language processing -- proved ineffective, shedding light on the unique challenges of recommendation models. To overcome this, we propose the Decoupled Attention and Representation Embeddings (DARE) model, where two distinct embedding tables are initialized and learned separately to fully decouple attention and representation. Extensive experiments and analysis demonstrate that DARE provides more accurate search of correlated behaviors and outperforms baselines with AUC gains up to 0.9% on public datasets and notable online system improvements. Furthermore, decoupling embedding spaces allows us to reduce the attention embedding dimension and accelerate the search procedure by 50% without significant performance impact, enabling more efficient, high-performance online serving.

The effectiveness of Recommender Systems (RS) is closely tied to the quality and distinctiveness of user profiles, yet despite many advancements in raw performance, the sensitivity of RS to user profile quality remains under-researched. This paper introduces novel information-theoretic measures for understanding recommender systems: a "surprise" measure quantifying users' deviations from popular choices, and a "conditional surprise" measure capturing user interaction coherence. We evaluate 7 recommendation algorithms across 9 datasets, revealing the relationships between our measures and standard performance metrics. Using a rigorous statistical framework, our analysis quantifies how much user profile density and information measures impact algorithm performance across domains. By segmenting users based on these measures, we achieve improved performance with reduced data and show that simpler algorithms can match complex ones for low-coherence users. Additionally, we employ our measures to analyze how well different recommendation algorithms maintain the coherence and diversity of user preferences in their predictions, providing insights into algorithm behavior. This work advances the theoretical understanding of user behavior and practical heuristics for personalized recommendation systems, promoting more efficient and adaptive architectures.

The widespread adoption of smartphones and Location-Based Social Networks has led to a massive influx of spatio-temporal data, creating unparalleled opportunities for enhancing Point-of-Interest (POI) recommendation systems. These advanced POI systems are crucial for enriching user experiences, enabling personalized interactions, and optimizing decision-making processes in the digital landscape. However, existing surveys tend to focus on traditional approaches and few of them delve into cutting-edge developments, emerging architectures, as well as security considerations in POI recommendations. To address this gap, our survey stands out by offering a comprehensive, up-to-date review of POI recommendation systems, covering advancements in models, architectures, and security aspects. We systematically examine the transition from traditional models to advanced techniques such as large language models. Additionally, we explore the architectural evolution from centralized to decentralized and federated learning systems, highlighting the improvements in scalability and privacy. Furthermore, we address the increasing importance of security, examining potential vulnerabilities and privacy-preserving approaches. Our taxonomy provides a structured overview of the current state of POI recommendation, while we also identify promising directions for future research in this rapidly advancing field.

Machine learning (ML) models trained on datasets owned by different organizations and physically located in remote databases offer benefits in many real-world use cases. State regulations or business requirements often prevent data transfer to a central location, making it difficult to utilize standard machine learning algorithms. Federated Learning (FL) is a technique that enables models to learn from distributed datasets without revealing the original data. Vertical Federated learning (VFL) is a type of FL where data samples are divided by features across several data owners. For instance, in a recommendation task, a user can interact with various sets of items, and the logs of these interactions are stored by different organizations. In this demo paper, we present \emph{Stalactite} - an open-source framework for VFL that provides the necessary functionality for building prototypes of VFL systems. It has several advantages over the existing frameworks. In particular, it allows researchers to focus on the algorithmic side rather than engineering and to easily deploy learning in a distributed environment. It implements several VFL algorithms and has a built-in homomorphic encryption layer. We demonstrate its use on a real-world recommendation datasets.

We typically see some Amazon devices, including Blink cameras, drop in price ahead of both Prime Days in July and October. This time around, Prime members have an exclusive deal available to them right now on a bundle that includes the Echo Show 5 smart display and a Blink Outdoor 4 camera system for only 60. This bundle is one that makes a lot of sense. You'll be able to use your Echo Show 5 to get a live view of whatever the Blink Outdoor 4 camera is capturing with a simple Alexa command. A bundle of the Blink Outdoor 4 camera and Echo Show 5 smart display has dropped to 60, the lowest price to date.

In 2017, Amazon launched the Echo Spot only to discontinue it two years later. This year, Amazon brought it back with new features and a fresh look. The 2024 edition is also 50 cheaper than its predecessor. But that 80 price tag is cut even more in a sale ahead of Prime Day. Right now, you can get the Amazon Echo Spot for just 45 -- a 44 percent discount.

Have you ever seen a movie where someone enters a posh home and immediately uses a big control panel to secure their house, turn on their lights, get news updates, and so on? That's essentially what a smart home hub does, and you can get one now at a great price if you want. The Amazon Echo Hub is a central control panel that connects all the smart home devices in your house, and right now it's on sale for just 125 on Amazon. Whether you place it by the door or put it in your bedroom, it doesn't matter because it just works. The Echo Hub's dashboard is customizable, so you can add in your favorite widgets, check in on your smart doorbell camera feed, quickly turn off the smart lights in your living room, send your smart robot vacuum on a cleaning job, or arm your security system.