26 April 2023 in IEEE Transactions on Knowledge and Data Engineering
Recently, with the superior capacity for analyzing the multiplex graph data, self-supervised multiplex graph representation learning (SMGRL) has received much interest. However, existing SMGRL methods are still limited by the following issues: (i) they generally ignore the noisy information within each graph and the common information among different graphs, thus weakening the effectiveness of SMGRL, and (ii) they conduct negative sample encoding and complex pretext tasks for contrastive learning, thus weakening the efficiency of SMGRL. To solve these issues, in this work, we propose a new framework to conduct effective and efficient SMGRL. Specifically, the proposed method investigates the intra-graph and inter-graph decorrelation losses, respectively, for reducing the impact of noisy information within each graph and capturing the common information among different graphs, to achieve the effectiveness. Moreover, the proposed method does not need negative samples for the SMGRL and designs a simple pretext task, to achieve the efficiency. We further theoretically justify that our method achieves the maximal mutual information instead of directly conducting contrastive learning and theoretically justify that our method actually minimizes the multiplex graph information bottleneck, which guarantees the effectiveness. In addition, an extension for semi-supervised scenarios is proposed to fit the case that a few labels are provided in reality. Extensive experimental results verify the effectiveness and efficiency of the proposed method with respect to various downstream tasks.
2 May 2017 in High Performance Polymers
Obtaining foams of poly-containing biphenyl moieties (phthalazinone ether sulfone ketone; PPBESK) by applying the microcellular injection molding method is very difficult because of the high melt viscosity of the materials used. To overcome this limitation, polyphenylene sulfide (PPS) was used to improve the rheological properties of PPBESK. PPBESK/PPS blends of different proportions were prepared using the melt mixing method. The rheological behavior, phase behavior, interfacial tension, and mechanical properties of the blends were then investigated. The results clearly indicate that PPS can improve the melt processability of PPBESK. However, due to the strong adhesion between the PPS and PPBESK phases, the introduction of PPS did not cause any loss of the mechanical and thermal properties of PPBESK. Accordingly, microcellular foams from modified PPBESK were prepared by microcellular injection molding with supercritical nitrogen as foaming agent. A closed cell microcellular morphology with an average cell size of 17.7 um and cell density of 109 cells cm−3 was obtained.
18 March 2025 in IEEE Transactions on Neural Networks and Learning Systems
Missing attribute completion for unattributed nodes in heterogeneous graphs has received increasing attention, but previous works still suffer from the following issues: 1) they ignore the noise in the raw attributes, resulting in noise propagation and even inaccurate information generation during attribute completion, thus further influencing the representation learning; and 2) they ignore constraints on unattributed nodes when conducting consistency learning across augmented graph views, resulting in data inconsistency across views. To solve these issues, in this article, we propose a new dual consistency constraint-based self-supervised representation learning method for heterogeneous graphs with missing attributes. Specifically, we first investigate the representation completion and the within-view consistency loss to complete missing information in the representation space, and then, we investigate the cross-view consistency loss to ensure data consistency across views. We further reconstruct the masked data to avoid information loss due to the masking process. As a result, our method effectively filters out noise and inaccurate information by the representation completion process as well as achieves discriminative representation learning for heterogeneous graphs with missing attributes. Experimental results on various downstream tasks verify the superiority of our method.