Knowledge graphs (KGs) have become widespread, and various knowledge graphs are constructed incessantly to support many in-KG and out-of-KG applications. During the construction of KGs, although new KGs may contain new entities with respect to constructed KGs, some entity-independent knowledge can be transferred from constructed KGs to new KGs. We call such knowledge meta-knowledge, and refer to the problem of transferring meta-knowledge from constructed (source) KGs to new (target) KGs to improve the performance of tasks on target KGs as meta-knowledge transfer for knowledge graphs. However, there is no available general framework that can tackle meta-knowledge transfer for both in-KG and out-of-KG tasks uniformly. Therefore, in this paper, we propose a framework, MorsE, which means conducting Meta-Learning for Meta-Knowledge Transfer via Knowledge Graph Embedding. MorsE represents the meta-knowledge via Knowledge Graph Embedding and learns the meta-knowledge by Meta-Learning. Specifically, MorsE uses an entity initializer and a Graph Neural Network (GNN) modulator to entity-independently obtain entity embeddings given a KG and is trained following the meta-learning setting to gain the ability of effectively obtaining embeddings. Experimental results on meta-knowledge transfer for both in-KG and out-of-KG tasks show that MorsE is able to learn and transfer meta-knowledge between KGs effectively, and outperforms existing state-of-the-art models.

Motivated by applications to resource-limited and safety-critical domains, we study selective classification in the online learning model, wherein a predictor may abstain from classifying an instance. For example, this may model an adaptive decision to invoke more resources on this instance. Two salient aspects of the setting we consider are that the data may be non-realisable, due to which abstention may be a valid long-term action, and that feedback is only received when the learner abstains, which models the fact that reliable labels are only available when the resource intensive processing is invoked. Within this framework, we explore strategies that make few mistakes, while not abstaining too many times more than the best-in-hindsight error-free classifier from a given class. That is, the one that makes no mistakes, while abstaining the fewest number of times. We construct simple versioning-based schemes for any $\mu \in (0,1],$ that make most $T^\mu$ mistakes while incurring \smash{$\tilde{O}(T^{1-\mu})$} excess abstention against adaptive adversaries. We further show that this dependence on $T$ is tight, and provide illustrative experiments on realistic datasets.

This paper presents a novel federated linear contextual bandits model, where individual clients face different $K$-armed stochastic bandits coupled through common global parameters. By leveraging the geometric structure of the linear rewards, a collaborative algorithm called Fed-PE is proposed to cope with the heterogeneity across clients without exchanging local feature vectors or raw data. Fed-PE relies on a novel multi-client G-optimal design, and achieves near-optimal regrets for both disjoint and shared parameter cases with logarithmic communication costs. In addition, a new concept called collinearly-dependent policies is introduced, based on which a tight minimax regret lower bound for the disjoint parameter case is derived. Experiments demonstrate the effectiveness of the proposed algorithms on both synthetic and real-world datasets.

Artificial intelligence (AI) systems offer effective support for online learning and teaching, including personalizing learning for students, automating instructors’ routine tasks, and powering adaptive assessments. However, while the opportunities for AI are promising, the impact of AI systems on the culture of, norms in, and expectations about interactions between students and instructors are still elusive. In online learning, learner–instructor interaction (inter alia, communication, support, and presence) has a profound impact on students’ satisfaction and learning outcomes. Thus, identifying how students and instructors perceive the impact of AI systems on their interaction is important to identify any gaps, challenges, or barriers preventing AI systems from achieving their intended potential and risking the safety of these interactions. To address this need for forward-looking decisions, we used Speed Dating with storyboards to analyze the authentic voices of 12 students and 11 instructors on diverse use cases of possible AI systems in online learning. Findings show that participants envision adopting AI systems in online learning can enable personalized learner–instructor interaction at scale but at the risk of violating social boundaries. Although AI systems have been positively recognized for improving the quantity and quality of communication, for providing just-in-time, personalized support for large-scale settings, and for improving the feeling of connection, there were concerns about responsibility, agency, and surveillance issues. These findings have implications for the design of AI systems to ensure explainability, human-in-the-loop, and careful data collection and presentation. Overall, contributions of this study include the design of AI system storyboards which are technically feasible and positively support learner–instructor interaction, capturing students’ and instructors’ concerns of AI systems through Speed Dating, and suggesting practical implications for maximizing the positive impact of AI systems while minimizing the negative ones.

The artificial intelligence market is booming, with an expected annual growth of 35.6% CAGR from 2021 to 2026. The demand for artificial intelligence experts is mounting as the economy widens and companies inflate their technology usage to improve their businesses. While this presents great opportunities for many to start a career in AI, gaining the in-demand skills can be a challenging task, especially when there is no guidance or conflicting guidance available. We have compiled a list of some of best online courses and Youtube channels which are freely available. Although various articles have published lists of top/best courses, most of them do not cater the requirement of the learners which could vary with their background.

Every application needs a front-end. The front-end part is very important, because this is the part the user is going to interact with. The front-end for this project is developed using html. The html code is created in Code Pen. Code Pen is a webpage, where users can create and visualize their html code online in an interactive environment.

Transfer learning is a machine learning technique in which a model trained on a specific task is reused as part of the training process for another, different task. Here is a simple analogy to help you understand how transfer learning works: imagine that one person has learned everything there is to know about dogs. In contrast, another person has learned everything about cats. If both people are asked, "What's an animal with four legs, a tail, and barks?" The person who knows all about dogs would answer "dog" while the individual who knows everything about cats would say "cat."

According to the China Disabled Persons' Federation (CDPF), there are now 17 million visually impaired people in China, among which three million are totally blind, while the others are low-visioned. In the past two decades, China has experienced tremendous development of information technology. Traditional industries are incorporating information technology, with services delivered to users through websites and mobile applications. It is positive technical progress that visually impaired people can access various services without leaving home; for example, they can order food delivery online or schedule a taxi from an app-based transportation service. However, the development of technology has also brought challenges to the visually impaired in China.

Computer system courses (for example, computer organization, computer architecture, operating system, and compiler) are the foundation of computer science education. However, it is difficult for undergraduates to fully grasp key concepts and principles of computer systems due to the gap between theory and practice. To mitigate the gap, Chinese educators have spent the last decade focusing on teaching undergraduates to build real computer systems. They carried out many effective reform measures with the philosophy of learning-by-doing, which have significantly improved the computer system skills and abilities of Chinese undergraduates. Chinese educators have devoted exhaustive efforts over the past 10 years to reform measures for improving the technical skills of undergraduates by teaching them to build real computer systems.

Artificial intelligence (AI) has the potential to enhance every technology as it resembles enabling technologies like the combustion engine or electricity. Many people in this field believe AI is general purpose, with a multitude of applications across many different disciplines. We believe the nature of AI is interdisciplinary. In other words, the power of AI lies in augmenting its ability to accelerate research exponentially and the possibilities are endless. As a result, demand for professionals who are hard-wired in AI technology knowledge but who also possess interdisciplinary perspectives and transferable skills is becoming increasingly important.