Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure.

Graph neural networks (GNNs) have achieved considerable success in dealing with graph-structured data by the message-passing mechanism. Actually, this mechanism relies on a fundamental assumption that the graph structure along which information propagates is perfect. However, the real-world graphs are inevitably incomplete or noisy, which violates the assumption, thus resulting in limited performance. Therefore, optimizing graph structure for GNNs is indispensable and important. Although current semi-supervised graph structure learning (GSL) methods have achieved a promising performance, the potential of labels and prior graph structure has not been fully exploited yet. Inspired by this, we examine GSL with dual reinforcement of label and prior structure in this article. Specifically, to enhance label utilization, we first propose to construct the prior label-constrained matrices to refine the graph structure by identifying label consistency. Second, to adequately leverage the prior structure to guide GSL, we develop spectral contrastive learning that extracts global properties embedded in the prior graph structure. Moreover, contrastive fusion with prior spatial structure is further adopted, which promotes the learned structure to integrate local spatial information from the prior graph. To extensively evaluate our proposal, we perform sufficient experiments on seven benchmark datasets, where experimental results confirm the effectiveness of our method and the rationality of the learned structure from various aspects.

Clustering Enhanced Multiplex Graph Contrastive Representation Learning.

Multiplex graph representation learning has attracted considerable attention due to its powerful capacity to depict multiple relation types between nodes. Previous methods generally learn representations of each relation-based subgraph and then aggregate them into final representations. Despite the enormous success, they commonly encounter two challenges: 1) the latent community structure is overlooked and 2) consistent and complementary information across relation types remains largely unexplored. To address these issues, we propose a clustering-enhanced multiplex graph contrastive representation learning model (CEMR). In CEMR, by formulating each relation type as a view, we propose a multiview graph clustering framework to discover the potential community structure, which promotes representations to incorporate global semantic correlations. Moreover, under the proposed multiview clustering framework, we develop cross-view contrastive learning and cross-view cosupervision modules to explore consistent and complementary information in different views, respectively. Specifically, the cross-view contrastive learning module equipped with a novel negative pairs selecting mechanism enables the view-specific representations to extract common knowledge across views. The cross-view cosupervision module exploits the high-confidence complementary information in one view to guide low-confidence clustering in other views by contrastive learning. Comprehensive experiments on four datasets confirm the superiority of our CEMR when compared to the state-of-the-art rivals.

Crumpled graphene microspheres anchored on NiCo2O4 nanoparticles as an advanced composite electrode for asymmetric supercapacitors with ultralong cycling life.

The rational design of composite electrodes that may take full advantage of pseudocapacitive metal oxides and graphene is still challenging. Herein, nickel cobaltate (NiCo2O4) nanoparticle-anchored crumpled graphene microspheres (CGMs) were fabricated through a simple spray-assisted self-assembly process and used as a composite electrode for aqueous supercapacitors. Due to the porous spherical architecture and well-dispersed NiCo2O4 nanoparticles on graphene, the NiCo2O4/CGM electrode displays ideal electrochemical performance, including a specific capacitance of 369.8 F g-1 (at 1 A g-1), good rate performance of 85% capacitance retention even at 10 A g-1 and intriguing cycling stability. An aqueous asymmetric supercapacitor (ASC) with an operating voltage of 1.6 V was then assembled using the NiCo2O4/CGM composite and nitrogen-doped CGM (N-CGM) as the positive and negative electrodes in KOH electrolyte, respectively. The ASC device exhibited an excellent energy density of 24.7 W h kg-1 at a power density of 799.6 W kg-1, and an ultralong cycling life with a capacitance retention of 85% after 50 000 cycles. The satisfactory electrochemical performance and ultralong cycling stability indicate that the NiCo2O4/CGM electrode has promising applications in advanced supercapacitors.

Fe3O4 nanoplates anchored on Ti3C2Tx MXene with enhanced pseudocapacitive and electrocatalytic properties.

Ti3C2Tx, as novel members of the two-dimensional material family, hold great promise for electrochemical energy storage and catalysis, however, the electrochemical performance of Ti3C2Tx is largely limited by the self-restacking of their layers due to van der Waals forces. In this study, we report a high-performance electrode material, Ti3C2Tx supported Fe3O4 nanoplates (denoted as MXene-Fe), synthesized by a simple in situ wet chemistry method in a solvothermal system. The mesoporous MXene-Fe material as a supercapacitor electrode exhibits a high specific capacitance of 368.0 F g-1 at 1.0 A g-1 and long cycling stability with about 81% capacitance retention after 10 000 cycles at 10.0 A g-1. Moreover, the optimized MXene-Fe also displays high electrocatalytic activity and stability toward the oxygen evolution reaction in alkaline solution (1.0 M KOH) with a low overpotential of 290 mV at 10 mA cm-2 and a small Tafel slope of 65.1 mV dec-1. This work provides an effective strategy for developing novel Ti3C2Tx-based functional materials with outstanding electrochemical performance for supercapacitors and electrocatalysis.