Federated Learning (FL) is a well-established technique for privacy preserving distributed training. Much attention has been given to various aspects of FL training. A growing number of applications that consume FL-trained models, however, increasingly operate under dynamically and unpredictably variable conditions, rendering a single model insufficient. We argue for training a global family of models cost efficiently in a federated fashion. Training them independently for different tradeoff points incurs $O(k)$ cost for any k architectures of interest, however. Straightforward applications of FL techniques to recent weight-shared training approaches is either infeasible or prohibitively expensive. We propose SuperFed - an architectural framework that incurs $O(1)$ cost to co-train a large family of models in a federated fashion by leveraging weight-shared learning. We achieve an order of magnitude cost savings on both communication and computation by proposing two novel training mechanisms: (a) distribution of weight-shared models to federated clients, (b) central aggregation of arbitrarily overlapping weight-shared model parameters. The combination of these mechanisms is shown to reach an order of magnitude (9.43x) reduction in computation and communication cost for training a $5*10^{18}$-sized family of models, compared to independently training as few as $k = 9$ DNNs without any accuracy loss.

Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system. Interactions in CIS are primarily based on natural language dialogue, while they may include other types of interactions, such as click, touch, and body gestures. This monograph provides a thorough overview of CIS definitions, applications, interactions, interfaces, design, implementation, and evaluation. This monograph views CIS applications as including conversational search, conversational question answering, and conversational recommendation. Our aim is to provide an overview of past research related to CIS, introduce the current state-of-the-art in CIS, highlight the challenges still being faced in the community. and suggest future directions.

If you're struggling to stay on top of your tasks or keep track of your notes, maybe what you need are some new tools. I'm always looking for better ways to stay organized. When I find a new app that sounds promising, I pit it against my existing tools in a game of survival of fittest, leaving only the ones that work best for me. These are currently the five services I rely on the most for note-taking, bookmarking, and task management. As we head into the new year, perhaps they'll provide just the kind of fresh inspiration you're looking for.

They can help you get an appointment or order a pizza, find the best ticket deals and bring your attention to the fact you are spending a lot on entertainment instead of investments. We are talking about AI virtual assistants, which have already become a familiar part of our daily lives. But what technologies are under the hood of AI assistants and how can you leverage them in your business? Find all the answers in this article. Intelligent Virtual Assistants (IVA) also known as Intelligent Personal Assistants (IPA) are AI-powered agents capable of generating personalized responses, pulling from contexts such as customer metadata, prior conversations, knowledge bases, geolocation, and other modular databases and plug-ins. The Intelligent Virtual Assistant market, experiencing rapid growth in the 2020s, is forecasted to reach USD 6.27 billion by 2026, according to Mordor Intelligence.

Quality education, one of the seventeen sustainable development goals (SDGs) identified by the United Nations General Assembly, stands to benefit enormously from the adoption of artificial intelligence (AI) driven tools and technologies. The concurrent boom of necessary infrastructure, digitized data and general social awareness has propelled massive research and development efforts in the artificial intelligence for education (AIEd) sector. In this review article, we investigate how artificial intelligence, machine learning and deep learning methods are being utilized to support students, educators and administrative staff. We do this through the lens of a novel categorization approach. We consider the involvement of AI-driven methods in the education process in its entirety - from students admissions, course scheduling etc. in the proactive planning phase to knowledge delivery, performance assessment etc. in the reactive execution phase. We outline and analyze the major research directions under proactive and reactive engagement of AI in education using a representative group of 194 original research articles published in the past two decades i.e., 2003 - 2022. We discuss the paradigm shifts in the solution approaches proposed, i.e., in the choice of data and algorithms used over this time. We further dive into how the COVID-19 pandemic challenged and reshaped the education landscape at the fag end of this time period. Finally, we pinpoint existing limitations in adopting artificial intelligence for education and reflect on the path forward.

Artificial intelligence is a game-changing development in the world of technology, and AI apps are regarded as one of the most significant breakthroughs in the field of information and technology. The AI App demonstrates the proclivity of human intelligence and its ability to take things to the next level in the world of science. To put it simply, artificial intelligence apps attempt to mimic the best way possible for humans to behave. These apps are said to shorten the time and effort required to complete a specific task or project. AI apps are used in a variety of applications ranging from business management to the healthcare system and so on. Regardless of their capabilities, you will find these Artificial Intelligence apps useful in making your work easier.

Netflix uses machine learning techniques, including matrix factorization, deep learning, and reinforcement learning, to power its recommendation system and deliver personalized recommendations to its users. Netflix is a leading streaming service that has revolutionized the way we consume TV shows and movies. One key factor in its success is its sophisticated recommendation system, which suggests content to users based on their past viewing history and preferences. In this article, we will explore how Netflix uses machine learning to power its recommendation system and deliver a personalized viewing experience to its users. Netflix's recommendation system is based on collaborative filtering, which involves gathering data on user behavior and preferences, and using this information to make recommendations to other users with similar tastes.

This paper proposes TRAININGCXL that can efficiently process large-scale recommendation datasets in the pool of disaggregated memory while making training fault tolerant with low overhead. To this end, i) we integrate persistent memory (PMEM) and GPU into a cache-coherent domain as Type-2. Enabling CXL allows PMEM to be directly placed in GPU's memory hierarchy, such that GPU can access PMEM without software intervention. TRAININGCXL introduces computing and checkpointing logic near the CXL controller, thereby training data and managing persistency in an active manner. Considering PMEM's vulnerability, ii) we utilize the unique characteristics of recommendation models and take the checkpointing overhead off the critical path of their training. Lastly, iii) TRAININGCXL employs an advanced checkpointing technique that relaxes the updating sequence of model parameters and embeddings across training batches. The evaluation shows that TRAININGCXL achieves 5.2x training performance improvement and 76% energy savings, compared to the modern PMEM-based recommendation systems.

Nowadays, many social media platforms are centered around content creators (CC). On these platforms, the tie formation process depends on two factors: (a) the exposure of users to CCs (decided by, e.g., a recommender system), and (b) the following decision-making process of users. Recent research studies underlined the importance of content quality by showing that under exploratory recommendation strategies, the network eventually converges to a state where the higher the quality of the CC, the higher their expected number of followers. In this paper, we extend prior work by (a) looking beyond averages to assess the fairness of the process and (b) investigating the importance of exploratory recommendations for achieving fair outcomes. Using an analytical approach, we show that non-exploratory recommendations converge fast but usually lead to unfair outcomes. Moreover, even with exploration, we are only guaranteed fair outcomes for the highest (and lowest) quality CCs.

Classifieds provide many challenges for recommendation methods, due to the limited information regarding users and items. In this paper, we explore recommendation methods for classifieds using the example of OLX Jobs. The goal of the paper is to benchmark different recommendation methods for jobs classifieds in order to improve advertisements' conversion rate and user satisfaction. In our research, we implemented methods that are scalable and represent different approaches to recommendation, namely ALS, LightFM, Prod2Vec, RP3beta, and SLIM. We performed a laboratory comparison of methods with regard to accuracy, diversity, and scalability (memory and time consumption during training and in prediction). Online A/B tests were also carried out by sending millions of messages with recommendations to evaluate models in a real-world setting. In addition, we have published the dataset that we created for the needs of our research. To the best of our knowledge, this is the first dataset of this kind. The dataset contains 65,502,201 events performed on OLX Jobs by 3,295,942 users, who interacted with (displayed, replied to, or bookmarked) 185,395 job ads in two weeks of 2020. We demonstrate that RP3beta, SLIM, and ALS perform significantly better than Prod2Vec and LightFM when tested in a laboratory setting. Online A/B tests also demonstrated that sending messages with recommendations generated by the ALS and RP3beta models increases the number of users contacting advertisers. Additionally, RP3beta had a 20% greater impact on this metric than ALS.