The biggest news in tech this week came from Google's annual developer conference on Wednesday. They announced three new devices: The Pixel 7a smartphone, the Pixel Tablet and the Pixel Fold. Discounts on brand new products don't happen often, but both Amazon and Google were quick to bundle Pixel 7a orders with a $50 Amazon gift card, or a free pair of Pixel Buds, respectively -- not sales per se, but free stuff is still compelling for anyone already planning on getting a new phone. Of course, there were deals unrelated to Google too, like savings on Amazon devices including the Fire TV Stick 4K Max, Echo speakers, and nearly all Kindle models. Here are the best tech deals from this week that you can still get today.

Existing recommender systems face difficulties with zero-shot items, i.e. items that have no historical interactions with users during the training stage. Though recent works extract universal item representation via pre-trained language models (PLMs), they ignore the crucial item relationships. This paper presents a novel paradigm for the Zero-Shot Item-based Recommendation (ZSIR) task, which pre-trains a model on product knowledge graph (PKG) to refine the item features from PLMs. We identify three challenges for pre-training PKG, which are multi-type relations in PKG, semantic divergence between item generic information and relations and domain discrepancy from PKG to downstream ZSIR task. We address the challenges by proposing four pre-training tasks and novel task-oriented adaptation (ToA) layers. Moreover, this paper discusses how to fine-tune the model on new recommendation task such that the ToA layers are adapted to ZSIR task. Comprehensive experiments on 18 markets dataset are conducted to verify the effectiveness of the proposed model in both knowledge prediction and ZSIR task.

We develop a novel latent-bandit algorithm for tackling the cold-start problem for new users joining a recommender system. This new algorithm significantly outperforms the state of the art, simultaneously achieving both higher accuracy and lower regret.

Twitter users are calling on Elon Musk to develop an AI-powered dating app called'Twinder,' touting it as the way'to save humanity from extinction.' The idea came after Musk replied'population collapse' to a tweet showing how fertility rates keep dropping in the Nordic countries. The potential dating app, which the Twitter CEO deemed an'interesting idea,' would use artificial intelligence to make matches instead of random swiping. The suggested service would feed AI Twitter accounts, including posts, comments and likes, and the technology would look for another user with similar behaviors and interests. The Twitter thread, viewed over two million times, has hundreds of comments, with some sharing how they met their partner on the social network.

Amazon's Echo speakers, and the Alexa assistant, are incredibly useful and pretty darn invasive. On the practical side, it can function as a security alarm with a device you already own. Here's how Alexa Guard works. I once found a voice recording of a conversation my Echo caught when I knew for sure I didn't ask Alexa to listen in. It just thought it heard the wake word.

Walden University students are actively using three AI tools, Linda, Charlotte and Julian to set themselves up for educational success. A Minnesota university is actively using several unique artificial intelligence (AI) models to help tutor students, complete assignments and bolster their verbal and non-verbal communication skills. Adtalem Chief Customer Officer Steve Tom has helped to deploy three distinct AI systems: Charlotte, Linda, and Julian at Walden University. The tools help counseling students prepare for their careers by working with "digital people" to cultivate communication and crisis management skills. Charlotte is a digital assistant chatbot that can help students stay on top of tasks and assignments to navigate a class curriculum efficiently.

Meta is not pivoting away from its signature product, the metaverse. Or at least that's what the Meta chief executive, Mark Zuckerberg, is arguing. Despite reports that sales teams at Meta have spent less time pitching the metaverse to advertisers, Zuckerberg claimed on the tech firm's latest quarterly earnings call that it's business as usual over at the company formerly known as Facebook. "A narrative has developed that we're somehow moving away from focusing on the metaverse vision, so I just want to say upfront that that's not accurate," the CEO said. But neither is the virtual reality world the only product Meta has bet its future on, Zuckerberg argued: "We've been focusing on both AI and the metaverse for years now, and we will continue to focus on both."

Privacy-preserving cross-domain recommendation (PPCDR) refers to preserving the privacy of users when transferring the knowledge from source domain to target domain for better performance, which is vital for the long-term development of recommender systems. Existing work on cross-domain recommendation (CDR) reaches advanced and satisfying recommendation performance, but mostly neglects preserving privacy. To fill this gap, we propose a privacy-preserving generative cross-domain recommendation (PPGenCDR) framework for PPCDR. PPGenCDR includes two main modules, i.e., stable privacy-preserving generator module, and robust cross-domain recommendation module. Specifically, the former isolates data from different domains with a generative adversarial network (GAN) based model, which stably estimates the distribution of private data in the source domain with Renyi differential privacy (RDP) technique. Then the latter aims to robustly leverage the perturbed but effective knowledge from the source domain with the raw data in target domain to improve recommendation performance. Three key modules, i.e., (1) selective privacy preserver, (2) GAN stabilizer, and (3) robustness conductor, guarantee the cost-effective trade-off between utility and privacy, the stability of GAN when using RDP, and the robustness of leveraging transferable knowledge accordingly. The extensive empirical studies on Douban and Amazon datasets demonstrate that PPGenCDR significantly outperforms the state-of-the-art recommendation models while preserving privacy.

In the past decades, recommender systems have attracted much attention in both research and industry communities, and a large number of studies have been devoted to developing effective recommendation models. Basically speaking, these models mainly learn the underlying user preference from historical behavior data, and then estimate the user-item matching relationships for recommendations. Inspired by the recent progress on large language models (LLMs), we take a different approach to developing the recommendation models, considering recommendation as instruction following by LLMs. The key idea is that the preferences or needs of a user can be expressed in natural language descriptions (called instructions), so that LLMs can understand and further execute the instruction for fulfilling the recommendation task. Instead of using public APIs of LLMs, we instruction tune an open-source LLM (3B Flan-T5-XL), in order to better adapt LLMs to recommender systems. For this purpose, we first design a general instruction format for describing the preference, intention, task form and context of a user in natural language. Then we manually design 39 instruction templates and automatically generate a large amount of user-personalized instruction data (252K instructions) with varying types of preferences and intentions. To demonstrate the effectiveness of our approach, we instantiate the instruction templates into several widely-studied recommendation (or search) tasks, and conduct extensive experiments on these tasks with real-world datasets. Experiment results show that the proposed approach can outperform several competitive baselines, including the powerful GPT-3.5, on these evaluation tasks. Our approach sheds light on developing more user-friendly recommender systems, in which users can freely communicate with the system and obtain more accurate recommendations via natural language instructions.

Prediction-based decision-making systems are becoming increasingly prevalent in various domains. Previous studies have demonstrated that such systems are vulnerable to runaway feedback loops, e.g., when police are repeatedly sent back to the same neighborhoods regardless of the actual rate of criminal activity, which exacerbate existing biases. In practice, the automated decisions have dynamic feedback effects on the system itself that can perpetuate over time, making it difficult for short-sighted design choices to control the system's evolution. While researchers started proposing longer-term solutions to prevent adverse outcomes (such as bias towards certain groups), these interventions largely depend on ad hoc modeling assumptions and a rigorous theoretical understanding of the feedback dynamics in ML-based decision-making systems is currently missing. In this paper, we use the language of dynamical systems theory, a branch of applied mathematics that deals with the analysis of the interconnection of systems with dynamic behaviors, to rigorously classify the different types of feedback loops in the ML-based decision-making pipeline. By reviewing existing scholarly work, we show that this classification covers many examples discussed in the algorithmic fairness community, thereby providing a unifying and principled framework to study feedback loops. By qualitative analysis, and through a simulation example of recommender systems, we show which specific types of ML biases are affected by each type of feedback loop. We find that the existence of feedback loops in the ML-based decision-making pipeline can perpetuate, reinforce, or even reduce ML biases.