Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. However, due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category, e.g., “man-eating-pizza, giraffe-eating-leaf”, and the severe inter-class similarity between different classes, e.g., “man-holding-plate, man-eating-pizza”, in model's latent space. The above challenges prevent current SGG methods from acquiring robust features for reliable relation prediction. In this paper, we claim that the predicate's category-inherent semantics can serve as class-wise prototypes in the semantic space for relieving the challenges. To the end, we propose the Prototype-based Embedding Network (PE-Net), which models entities/predicates with prototype-aligned compact and distinctive representations and thereby establishes matching between entity pairs and predicates in a common embedding space for relation recognition. Moreover, Prototype-guided Learning (PL) is introduced to help PE-Net efficiently learn such entity-predicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching caused by the predicate's semantic overlap. Extensive experiments demonstrate that our method gains superior relation recognition capability on SGG, achieving new state-of-the-art performances on both Visual Genome and Open Images datasets. The codes are available at https://github.com/VL-Group/PENET.

Optimal join order selection often leads to optimal query execution plans while traversing the solution space is almost impossible which expands rapidly with the increase of join complexity. In the past research, considerable attention has been paid to heuristic rules for pruning. However, that may not work well facing complex SQL queries. Recent use of the reinforcement learning avoids traversing the solution space, but inaccurate long-term rewards may be obtained because of the inconsistent influence of various parts in the join tree. In this paper, SOAR is proposed, a novel learned optimizer that selects join orders through reinforcement learning with graph attention network. SOAR captures the tree structure by inputting the join tree in which each node carries database features into graph neural network and learns the inconsistent influence of join tree on long-term reward with graph attention mechanism in the process of reinforcement learning. The preliminary results demonstrate that SOAR can match or outperform the optimizer in PostgreSQL.

Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts, especially user-generated social media content.Semantic augmentation is a potential way to alleviate this problem.Given that rich semantic information is implicitly preserved in pre-trained word embeddings, they are potential ideal resources for semantic augmentation.In this paper, we propose a neural-based approach to NER for social media texts where both local (from running text) and augmented semantics are taken into account.In particular, we obtain the augmented semantic information from a large-scale corpus, and propose an attentive semantic augmentation module and a gate module to encode and aggregate such information, respectively.Extensive experiments are performed on three benchmark datasets collected from English and Chinese social media platforms, where the results demonstrate the superiority of our approach to previous studies across all three datasets.1 * Equal contribution.