Graph neural networks (GNNs) have made rapid developments in the recent years. Due to their great ability in modeling graph-structured data, GNNs are vastly used in various applications, including high-stakes scenarios such as financial analysis, traffic predictions, and drug discovery. Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society. For example, existing works demonstrate that attackers can fool the GNNs to give the outcome they desire with unnoticeable perturbation on training graph. GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias. Consequently, trust-worthy GNNs in various aspects are emerging to prevent the harm from GNN models and increase the users’ trust in GNNs. In this paper, we give a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability. For each aspect, we give the taxonomy of the related methods and formulate the general frameworks for the multiple categories of trustworthy GNNs. We also discuss the future research directions of each aspect and connections between these aspects to help achieve trustworthiness.

While China has become the biggest online market in the world with around 1 billion internet users, Baidu runs the world largest Chinese search engine serving more than hundreds of millions of daily active users and responding to billions of queries per day. To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieving relevant content from a pool of trillions of webpages, and ranking the most relevant webpages on the top of results. Among these components used in Baidu search, learning to rank (LTR) plays a critical role and we need to timely label an extremely large number of queries together with relevant webpages to train and update the online LTR models. To reduce the costs and time consumption of queries/webpages labeling, we study the problem of Active Learning to Rank (active LTR) that selects unlabeled queries for annotation and training in this work. Specifically, we first investigate the criterion-Ranking Entropy (RE) characterizing the entropy of relevant webpages under a query produced by a sequence of online LTR models updated by different checkpoints, using a Query-By-Committee (QBC) method. Then, we explore a new criterion namely Prediction Variances (PV) that measures the variance of prediction results for all relevant webpages under a query. Our empirical studies find that RE may favor low-frequency queries from the pool for labeling while PV prioritizes high-frequency queries more. Finally, we combine these two complementary criteria as the sample selection strategies for active learning. Extensive experiments with comparisons to baseline algorithms show that the proposed approach could train LTR

As an innovative engine for digital content generation, AI-generated content (AIGC) has drawn more and more attention from academic fields as well as industries. Specifically in the area of art creation, AI has demonstrated its great potential and gained increasing popularity. People are greatly impressed by AI painting, composing, writing, virtual hosting, fashion, and design. Moreover, AI is also becoming capable of understanding art, evalu-Editorial Special Issue on Artificial Intelligence for Art

Given a task, human learns from easy to hard, whereas the model learns randomly. Undeniably, difficulty insensitive learning leads to great success in NLP, but little attention has been paid to the effect of text difficulty in NLP. In this research, we propose the Human Learning Matching Index (HLM Index) to investigate the effect of text difficulty. Experiment results show: (1) LSTM has more human-like learning behavior than BERT. (2) UID-SuperLinear gives the best evaluation of text difficulty among four text difficulty criteria. (3) Among nine tasks, some tasks' performance is related to text difficulty, whereas some are not. ( 4) Model trained on easy data performs best in easy and medium data, whereas trains on a hard level only perform well on hard data. ( 5) Training the model from easy to hard leads to fast convergence. 1