Predicting Click-Through Rates is a crucial function within recommendation and advertising platforms, as the output of CTR prediction determines the order of items shown to users. The Embedding \& MLP paradigm has become a standard approach for industrial recommendation systems and has been widely deployed. However, this paradigm suffers from cold-start problems, where there is either no or only limited user action data available, leading to poorly learned ID embeddings. The cold-start problem hampers the performance of new items. To address this problem, we designed a novel diffusion model to generate a warmed-up embedding for new items. Specifically, we define a novel diffusion process between the ID embedding space and the side information space. In addition, we can derive a sub-sequence from the diffusion steps to expedite training, given that our diffusion model is non-Markovian. Our diffusion model is supervised by both the variational inference and binary cross-entropy objectives, enabling it to generate warmed-up embeddings for items in both the cold-start and warm-up phases. Additionally, we have conducted extensive experiments on three recommendation datasets. The results confirmed the effectiveness of our approach.

'The Big Weekend Show' co-hosts discuss Tinder user traffic peaking during'Dating Sunday.' A New Jersey woman is accused of hiring a man she met on Tinder to kill her police officer ex-boyfriend and his daughter, according to authorities. Camden County Prosecutor Grace C. MacAulay charged Jaclyn Diiorio, 26, with two counts of attempted first-degree murder, one count of conspiracy to commit murder and one count of third-degree possession of a controlled dangerous substance in connection with the alleged crime. Diiorio, of Runnemede, allegedly told a confidential informant she met on Tinder that she wanted her ex, a 53-year-old Philadelphia Police Department officer, and his 19-year-old daughter killed, Gloucester New Jersey Township Police said in a news release. The informant and Diiorio allegedly exchanged several phone calls and text messages after meeting on the dating app and later in person at a Wawa, according to court documents obtained by Fox News Digital.

Finding love in Washington state could come with a price. A bill proposed by two state Democratic lawmakers would impose a tax on dating apps. Under the terms of House Bill 2071, dating app companies would be required to pay 1 per Washington-based user each month, regardless of whether the user pays for the service. The money would be used to fund domestic violence programs. The money would be put into the newly created state Domestic Violence Services Account, which funds intervention programs and support services for victims.

In the era of advancing information technology, recommender systems have emerged as crucial tools for dealing with information overload. However, traditional recommender systems still have limitations in capturing the dynamic evolution of user behavior. To better understand and predict user behavior, especially taking into account the complexity of temporal evolution, sequential recommender systems have gradually become the focus of research. Currently, many sequential recommendation algorithms ignore the amplification effects of prevalent biases, which leads to recommendation results being susceptible to the Matthew Effect. Additionally, it will impose limitations on the recommender system's ability to deeply perceive and capture the dynamic shifts in user preferences, thereby diminishing the extent of its recommendation reach. To address this issue effectively, we propose a recommendation system based on sequential information and attention mechanism called Multi-Perspective Attention Bias Sequential Recommendation (MABSRec). Firstly, we reconstruct user sequences into three short types and utilize graph neural networks for item weighting. Subsequently, an adaptive multi-bias perspective attention module is proposed to enhance the accuracy of recommendations. Experimental results show that the MABSRec model exhibits significant advantages in all evaluation metrics, demonstrating its excellent performance in the sequence recommendation task.

Multi-task learning (MTL) is a common machine learning technique that allows the model to share information across different tasks and improve the accuracy of recommendations for all of them. Many existing MTL implementations suffer from scalability issues as the training and inference performance can degrade with the increasing number of tasks, which can limit production use case scenarios for MTL-based recommender systems. Inspired by the recent advances of large language models, we developed an end-to-end efficient and scalable Generalist Recommender (GRec). GRec takes comprehensive data signals by utilizing NLP heads, parallel Transformers, as well as a wide and deep structure to process multi-modal inputs. These inputs are then combined and fed through a newly proposed task-sentence level routing mechanism to scale the model capabilities on multiple tasks without compromising performance. Offline evaluations and online experiments show that GRec significantly outperforms our previous recommender solutions. GRec has been successfully deployed on one of the largest telecom websites and apps, effectively managing high volumes of online traffic every day.

Generative recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. Most existing methods attempt to leverage prior knowledge embedded in Pre-trained Language Models (PLMs) to improve the recommendation performance. However, they often fail to accommodate the differences between the general linguistic knowledge of PLMs and the specific needs of recommendation systems. Moreover, they rarely consider the complementary knowledge between the multimodal information of items, which represents the multi-faceted preferences of users. To facilitate efficient recommendation knowledge transfer, we propose a novel approach called Multimodal Quantitative Language for Generative Recommendation (MQL4GRec). Our key idea is to transform items from different domains and modalities into a unified language, which can serve as a bridge for transferring recommendation knowledge. Specifically, we first introduce quantitative translators to convert the text and image content of items from various domains into a new and concise language, known as quantitative language, with all items sharing the same vocabulary. Then, we design a series of quantitative language generation tasks to enrich quantitative language with semantic information and prior knowledge. Finally, we achieve the transfer of recommendation knowledge from different domains and modalities to the recommendation task through pre-training and fine-tuning. We evaluate the effectiveness of MQL4GRec through extensive experiments and comparisons with existing methods, achieving improvements over the baseline by 11.18\%, 14.82\%, and 7.95\% on the NDCG metric across three different datasets, respectively.

Sequential recommendation is an advanced recommendation technique that utilizes the sequence of user behaviors to generate personalized suggestions by modeling the temporal dependencies and patterns in user preferences. However, it requires a server to centrally collect users' data, which poses a threat to the data privacy of different users. In recent years, federated learning has emerged as a distributed architecture that allows participants to train a global model while keeping their private data locally. This survey pioneers Federated Sequential Recommendation (FedSR), where each user joins as a participant in federated training to achieve a recommendation service that balances data privacy and model performance. We begin with an introduction to the background and unique challenges of FedSR. Then, we review existing solutions from two levels, each of which includes two specific techniques. Additionally, we discuss the critical challenges and future research directions in FedSR.

An AI-powered smart home voice assistant that amiably chats with you, follows your orders with ease, and does your bidding in the background? It's a tantalizing idea that seems so close, yet remains stubbornly far away. The big prediction last year was that a new Apple smart hub powered by an AI-augmented Siri would arrive by spring 2025--right around now--complete with a touchscreen and smart home controls. It was a device that would vault Apple back into the smart home game. And then there was Google, which had begun testing Gemini on its Nest smart speakers late last year, allowing a small subset of its users to chat with the powerful AI model when asking more complex questions.

In this study, we establish a unified framework to deal with the high dimensional matrix completion problem under flexible nonignorable missing mechanisms. Although the matrix completion problem has attracted much attention over the years, there are very sparse works that consider the nonignorable missing mechanism. To address this problem, we derive a row- and column-wise matrix U-statistics type loss function, with the nuclear norm for regularization. A singular value proximal gradient algorithm is developed to solve the proposed optimization problem. We prove the non-asymptotic upper bound of the estimation error's Frobenius norm and show the performance of our method through numerical simulations and real data analysis.

We study how to use naturally available user feedback, such as clicks, to optimize large language model (LLM) pipelines for generating personalized sentences using prompts. Naive approaches, which estimate the policy gradient in the prompt space, suffer either from variance caused by the large action space of prompts or bias caused by inaccurate reward predictions. To circumvent these challenges, we propose a novel kernel-based off-policy gradient method, which estimates the policy gradient by leveraging similarity among generated sentences, substantially reducing variance while suppressing the bias. Empirical results on our newly established suite of benchmarks demonstrate the effectiveness of the proposed approach in generating personalized descriptions for movie recommendations, particularly when the number of candidate prompts is large.