Learning effective recipe representations is essential in food studies.
Recently, contrastiveness-based augmentation surges a new climax in the computer vision domain, where some operations, including rotation, crop, and flip, combined with dedicated algorithms, dramatically increase the model generalization and robustness.
In light of this, few-shot learning on graphs (FSLG), which combines the strengths of graph representation learning and few-shot learning together, has been proposed to tackle the performance degradation in face of limited annotated data challenge.
In this paper, we propose a holistic framework named MetaHG to automatically detect illicit drug traffickers on social media (i. e., Instagram), by tackling the following two new challenges: (1) different from existing works which merely focus on analyzing post content, MetaHG is capable of jointly modeling multi-modal content and relational structured information on social media for illicit drug trafficker detection; (2) in addition, through the proposed meta-learning technique, MetaHG addresses the issue of requiring sufficient data for model training.
To retain the heterogeneity, intra-relation aggregation is first performed over each slice of HTG to attentively aggregate information of neighbors with the same type of relation, and then intra-relation aggregation is exploited to gather information over different types of relations; to handle temporal dependencies, across-time aggregation is conducted to exchange information across different graph slices over the HTG.
The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery.
Ranked #1 on Molecular Property Prediction (1-shot)) on Tox21
Multi-hop relation reasoning over knowledge base is to generate effective and interpretable relation prediction through reasoning paths.
This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario.
Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems.
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications.
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
Subsequently, given the signature matrices, a convolutional encoder is employed to encode the inter-sensor (time series) correlations and an attention based Convolutional Long-Short Term Memory (ConvLSTM) network is developed to capture the temporal patterns.