Graph representation learning resurges as a trending research subject owing to the widespread use of deep learning for Euclidean data, which inspire various creative designs of neural networks in the non-Euclidean domain, particularly graphs. With the success of these graph neural networks (GNN) in the static setting, we approach further practical scenarios where the graph dynamically evolves. Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics. These methods require the knowledge of a node in the full time span (including both training and testing) and are less applicable to the frequent change of the node set. In some extreme scenarios, the node sets at different time steps may completely differ. To resolve this challenge, we propose EvolveGCN, which adapts the graph convolutional network (GCN) model along the temporal dimension without resorting to node embeddings. The proposed approach captures the dynamism of the graph sequence through using an RNN to evolve the GCN parameters. Two architectures are considered for the parameter evolution. We evaluate the proposed approach on tasks including link prediction, edge classification, and node classification. The experimental results indicate a generally higher performance of EvolveGCN compared with related approaches. The code is available at https://github.com/IBM/EvolveGCN.

A sol-gel method was applied for the development of highly permeable hydrogen separation membranes using bis(triethoxysilyl)ethane (BTESE) as a silica precursor. Hybrid silica membranes showed quite high hydrogen permeance (1 x 10(-5) mol m(-2) s(-1) Pa(-1)) with a high H(2)-to-SF(6) selectivity of 1000 because of loose organic-inorganic silica networks. Hybrid silica membranes were found to show high hydrothermal stability due to the presence of Si-C-C-Si bonds in silica networks.

No abstract

in Wiley InterScience (www.interscience.wiley.com).DDR-type zeolite membranes were prepared by the secondary growth method on porous a-alumina disk, followed by on-stream counter diffusion chemical vapor deposition modification to eliminate the intercrystalline micropores. Single gas permeation of He, H 2 , CO 2 , and CO through this zeolite membrane before and after CVD modification was measured in 25-5008C. Intracrystalline diffusivities for these four gases in DDR-type zeolite were obtained from the permeation data above 3008C to examine the effects of the size and molecular weight of permeating gases on diffusion and permeation rate for this zeolite membrane. For the unmodified DDR-type zeolite membrane with presence of a small amount intercrystalline micropores the diffusivity (or permeance) with a low activation energy depends on both the size and molecular weight of permeating gases. For the CVD-modified DDR-type zeolite membrane with intercrystalline micropores eliminated, the activation energy for diffusion and diffusivity increases with increasing molecular size of the permeating gases.

No abstract

Organic/inorganic hybrid silica membranes were prepared from 1,1,3,3‐tetraethoxy‐1,3‐dimethyl disiloxane (TEDMDS) by the sol‐gel technique with firing at 300–550°C in N2. TEDMDS‐derived silica membranes showed high H2 permeance (0.3–1.1 × 10−6 mol m−2 s−1 Pa−1) with low H2/N2 (∼10) and high H2/SF6 (∼1200) perm‐selectivity, confirming successful tuning of micropore sizes larger than TEOS‐derived silica membranes. TEDMDS‐derived silica membranes prepared at 550°C in N2 increased gas permeances as well as pore sizes after air exposure at 450°C. TEDMDS had an advantage in tuning pore size by the “template” and “spacer” techniques, due to the pyrolysis of methyl groups in air and SiOSi bonding, respectively. For pore size evaluation of microporous membranes, normalized Knudsen‐based permeance, which was proposed based on the gas translation model and verified with permeance of zeolite membranes, reveals that pore sizes of TEDMDS membranes were successfully tuned in the range of 0.6–1.0 nm. © 2011 American Institute of Chemical Engineers AIChE J, 2011

No abstract

Bis(triethoxysilyl)methane (BTESM), which consists of Si–C–Si bonds, was used as a membrane precursor to control the size of amorphous silica networks. The single gas permeation characteristics of hybrid silica membranes were examined to determine the effect of silica precursors on amorphous networks. Pore size distribution, as determined by single gas permeation, suggested that average pore size was in the following order: bis(triethoxysilyl)ethane (BTESE)-derived silica > BTESM-derived silica > tetraethoxysilane (TEOS)-derived silica, due to differences in the minimum units of the silica precursor. The high C3H6/C3H8 separation performance of BTESM-derived silica membranes in a wide temperature range (50–200 °C) can be due to the control of silica network size by the “spacer” method using a Si–C–Si unit. For example, a BTESM-derived silica membrane showed a high C3H6 permeance of 6.32 × 10–7 mol m–2 s–1 Pa–1 with a C3H6/C3H8 permeance ratio of 8.8 at 50 °C. The order of C3H6 and C3H8 permeances of BTESM-derived silica membranes was C3H6 > C3H8, independent of the number of sol coats and temperature (50–200 °C), although the kinetic diameter of C3H6 (d k = 0.45 nm) was reported to be larger than that of C3H8 (d k = 0.43 nm). For permeation of hydrocarbons through amorphous silica membranes, it is suggested that the kinetic diameter, which is a minimum equilibrium cross-sectional diameter, is not applicable for effective molecular size, probably because diffusivity depends not only on the minimum cross section but also on molecular length.