Training recommendation systems (RecSys) faces several challenges as it requires the "data preprocessing" stage to preprocess an ample amount of raw data and feed them to the GPU for training in a seamless manner. To sustain high training throughput, state-of-the-art solutions reserve a large fleet of CPU servers for preprocessing which incurs substantial deployment cost and power consumption. Our characterization reveals that prior CPU-centric preprocessing is bottlenecked on feature generation and feature normalization operations as it fails to reap out the abundant inter-/intra-feature parallelism in RecSys preprocessing. PreSto is a storage-centric preprocessing system leveraging In-Storage Processing (ISP), which offloads the bottlenecked preprocessing operations to our ISP units. We show that PreSto outperforms the baseline CPU-centric system with a $9.6\times$ speedup in end-to-end preprocessing time, $4.3\times$ enhancement in cost-efficiency, and $11.3\times$ improvement in energyefficiency on average for production-scale RecSys preprocessing.

Collaborative Filtering (CF) typically suffers from the significant challenge of popularity bias due to the uneven distribution of items in real-world datasets. This bias leads to a significant accuracy gap between popular and unpopular items. It not only hinders accurate user preference understanding but also exacerbates the Matthew effect in recommendation systems. To alleviate popularity bias, existing efforts focus on emphasizing unpopular items or separating the correlation between item representations and their popularity. Despite the effectiveness, existing works still face two persistent challenges: (1) how to extract common supervision signals from popular items to improve the unpopular item representations, and (2) how to alleviate the representation separation caused by popularity bias. In this work, we conduct an empirical analysis of popularity bias and propose Popularity-Aware Alignment and Contrast (PAAC) to address two challenges. Specifically, we use the common supervisory signals modeled in popular item representations and propose a novel popularity-aware supervised alignment module to learn unpopular item representations. Additionally, we suggest re-weighting the contrastive learning loss to mitigate the representation separation from a popularity-centric perspective. Finally, we validate the effectiveness and rationale of PAAC in mitigating popularity bias through extensive experiments on three real-world datasets. Our code is available at https://github.com/miaomiao-cai2/KDD2024-PAAC.

Apple unveiled a new feature with its upcoming iOS 18 that has sparked controversy among users - with some saying it is'a cheater's paradise.' The new update will let uses hide or lock apps on their iPhone home screen, keeping their personal hobbies and information from prying eyes. While Apple touted it as keeping banking apps private and stopping kids from buying items on Amazon, many people see the feature as helping partners cheat easily. Social media erupted with posts about the new app, some calling it'sick' while others praised the new feature for letting them hide dating apps from their spouse. Apple unveiled a new feature with its upcoming iOS 18 that has sparked controversy among users - with some saying it is'a cheater's paradise' 'Users can now lock an app; and for additional privacy, they can hide an app, moving it to a locked, hidden apps folder,' Apple shared in an announcement following its Worldwide Developers Conference on Monday.

Today's keynote for Apple's Worldwide Developers Conference teased a lot of what users can expect later this year when all of its major software updates roll out. Big changes coming to iOS 18, macOS Sequoia and watchOS 11 include RCS support, a new Passwords app, a revamped Calculator app and a bunch of artificial intelligence (AI) infusions across the board thanks to the new "Apple Intelligence" system. If you weren't able to catch the news live, here's a rundown of everything announced at WWDC 2024. Apple revealed its plans to incorporate AI into its operating systems at WWDC this year. Dubbed "Apple Intelligence," this new generative AI system will appear in iOS and iPad 18 and macOS Sequoia in the form of (what Apple believes to be) practical tools that most people can use regularly.

As expected, Apple's assistant is about to get much more helpful thanks to a load of new AI-powered capabilities. During WWDC, the company previewed a new version of Siri that can take actions on your behalf and understand a wide range of new queries. The new version of Siri has a better understanding of the apps on your phone and will be able to take more than 100 actions based on your activity and device. For example, you could ask Siri to show you specific photos or memories in your Photos app or to find tracking details for an expected delivery from an email in the Mail app. Siri will also be able to perform some tasks for you, like adding an address to a contact card, tweak a photo, or share a summary of your notes in an email.

At WWDC 2024, Apple revealed a few key updates coming to AirPods this year. First, the company is adding a new head-nodding gesture on AirPods Pro that allows you to respond to Siri in crowded places where you'd rather not speak. You'll be able to nod affirmatively to silently say "yes" or shake your head for "no" and the voice assistant will react accordingly. In a demo, Apple showed a man in a crowded elevator shaking his head to tell Siri he didn't want to take a call from "Gam Gam."

Nothing official has been said yet about Apple's agreement with OpenAI to incorporate the Microsoft-owned company's ChatGPT into its well-known iOS voice-based personal assistant Siri, but here's what we know going into WWDC 2024 today. Apple's vice president of corporate development, Adrian Perica, has been quietly leading the charge to integrate the two, according to anonymous sources who spoke to the New York Times -- with the hope that the end result will be a Siri that's more conversational and versatile. Unlike its rivals however, Apple's core brand has been built on being intuitive and easy to use for the average person, so the company is the least likely to take any big risks with its AI offering. 'Apple is pretty conservative when it comes to everything, so I don't know that they will "wow" people,' Carolina Milanesi, president of Creative Strategies, a tech research firm, told the Times. 'But they have to do this because it will be how we interact with technology going forward,' she said.

The fourth-gen Amazon Echo smart speaker in white is on sale for 65, and the deal includes a Sengled Bluetooth smart light bulb. This is a discount of 40 percent. This is 40 percent off. This Echo easily made our list of the best smart speakers. We really appreciate just how loud this thing can get, especially when compared to competing speakers.

When it comes to smart speakers, the right one for you boils down to which personal assistant you'd prefer to have at your disposal. And if you lean towards Alexa, then this discounted Amazon Echo 4th Gen that's on sale for 65 should catch your eye. The Echo is rarely available for a better price outside of major sales events. This little speaker ball delivers high-quality sound that adapts to any room, enhancing your listening experience. But the Echo 4th Gen is more than just a smart speaker--it can be your home's smart hub, able to control any Alexa-compatible device on the same home network.

This article investigates the deployment of a Voice User Interface (VUI)-powered digital assistant in a retail setting and assesses its impact on customer engagement and service efficiency. The study explores how digital assistants can enhance user interactions through advanced conversational capabilities with multilingual support. By integrating a digital assistant into a high-traffic retail environment, we evaluate its effectiveness in improving the quality of customer service and operational efficiency. Data collected during the experiment demonstrate varied impacts on customer interaction, revealing insights into the future optimizations of digital assistant technologies in customer-facing roles. This study contributes to the understanding of digital transformation strategies within the customer relations domain emphasizing the need for service flexibility and user-centric design in modern retail stores.