A universal network strategy for lightspeed computation of entropy-regularized optimal transport.

Optimal transport (OT) is an effective tool for measuring discrepancies in probability distributions and histograms of features. To reduce its high computational complexity, entropy-regularized OT is proposed, which is computed through Sinkhorn algorithm and can be readily integrated into neural networks. However, each time the parameters of networks are updated, both the value and derivative of OT need to be calculated.

A high-performance TPGDA/PETEA composite gel polymer electrolyte for lithium metal batteries.

A gel polymer electrolyte (GPE) supported by a polyimide (PI) nanofiber membrane with LiLaZrTaO (LLZTO) nanoparticles (PI/LLZTO/GPE) shows excellent flexibility and electrochemical properties, the ionic conductivity is 1.87 mS cm and the Li transfer number is 0.64 at room temperature.

Latent neighborhood-based heterogeneous graph representation.

Graph, as a powerful data structure, has shown superior capability on modeling complex systems. Since real-world objects and their interactions are often multi-modal and multi-typed, compared with traditional homogeneous graphs, heterogeneous graphs can represent real-world objects more effectively. Meanwhile, rich semantic information brings great challenges for learning heterogeneous graph representation (HGR).

Graph Influence Network.

Due to the extraordinary abilities in extracting complex patterns, graph neural networks (GNNs) have demonstrated strong performances and received increasing attention in recent years. Despite their prominent achievements, recent GNNs do not pay enough attention to discriminate nodes when determining the information sources. Some of them select information sources from all or part of neighbors without distinction, and others merely distinguish nodes according to either graph structures or node features.

DREAM: Drug-drug interaction extraction with enhanced dependency graph and attention mechanism.

Drug-drug interactions (DDIs) aim at describing the effect relations produced by a combination of two or more drugs. It is an important semantic processing task in the field of bioinformatics such as pharmacovigilance and clinical research. Recently, graph neural networks are applied on dependency graph to promote the performance of DDI extraction with better semantic representations.

The effects of Al-doped to cathode material based on hollow microspheres of nickel-manganese on sodium-ion batteries.

Sodium-ion batteries (SIBs) are expected to be a great substitute for lithium ion batteries. Although there are many difficulties to overcome, SIBs have become one of the most important research areas for large-scale energy storage equipment. The spherical particles are conducive to the contact between the cathode material and the electrolyte, which could increase the electrochemical reaction area, and improve the deintercalation rate of sodium ions during charging and discharging.

Distant Supervision Relation Extraction via adaptive dependency-path and additional knowledge graph supervision.

Relation Extraction systems train an extractor by aligning relation instances in Knowledge Base with a large amount of labeled corpora. Since the labeled datasets are very expensive, Distant Supervision Relation Extraction (DSRE) utilizes rough corpus annotated with Knowledge Graph to reduce the cost of acquisition. Nevertheless, the data noise problem limits the performance of the DSRE.

DigGCN: Learning Compact Graph Convolutional Networks via Diffusion Aggregation.

Recent interests in graph neural networks (GNNs) have received increasing concerns due to their superior ability in the network embedding field. The GNNs typically follow a message passing scheme and represent nodes by aggregating features from neighbors. However, the current aggregation methods assume that the network structure is static and define the local receptive fields under visible connections, which consequently fails to consider latent or high-order structures.