As heterogeneous networks have become increasingly ubiquitous, Heterogeneous Information Network (HIN) embedding, aiming to project nodes into a low-dimensional space while preserving the heterogeneous structure, has drawn increasing attention in recent years. Many of the existing HIN embedding methods adopt meta-path guided random walk to retain both the semantics and structural correlations between different types of nodes. However, the selection of meta-paths is still an open problem, which either depends on domain knowledge or is learned from label information. As a uniform blueprint of HIN, the network schema comprehensively embraces the high-order structure and contains rich semantics. In this paper, we make the first attempt to study network schema preserving HIN embedding, and propose a novel model named NSHE. In NSHE, a network schema sampling method is first proposed to generate sub-graphs (i.e., schema instances), and then multi-task learning task is built to preserve the heterogeneous structure of each schema instance. Besides preserving pairwise structure information, NSHE is able to retain high-order structure (i.e., network schema). Extensive experiments on three real-world datasets demonstrate that our proposed model NSHE significantly outperforms the state-of-the-art methods.

No abstract

No abstract

No abstract

Blackleg (Phoma) disease, caused by the ascomycete fungi Plenodomus biglobosus and P. lingam, threatens oilseed rape (OSR; Brassica napus) crops internationally. In many parts of the world, both species co-occur, but in China only P. biglobosus has so far been reported. Plenodomus biglobosus reproduces asexually (pycnidiospores), but also sexually (pseudothecia-yielding ascospores), via a heterothallic mating system requiring MAT1-1 and MAT1-2 genotypes. However, the roles of airborne ascospore inoculum in driving blackleg disease outbreaks in China are less well understood compared to elsewhere in the world. This is despite the very different agronomic cropping practices in parts of China, in which paddy rice and OSR are often grown in rotation; OSR stubble is often submerged under water for long periods potentially affecting pseudothecial development. Here, we indirectly investigate the potential role of sexual reproduction by developing new polymerase chain reaction (PCR) -based mating-type diagnostics for P. biglobosus and subsequently screening an international collection of 59 European and 157 Chinese isolates. Overall, in both Europe and China, P. biglobosus mating types did not deviate from a 1:1 ratio, such as is generally thought to occur under frequency-dependent selection in sexually reproducing pathogen populations. Both mating types were balanced in all the individual European countries tested (Austria, France, Poland, UK). Conversely, in China, mating types were only balanced in the eastern region; in the northern and southwestern regions there were skewed ratios, more typical of predominantly asexual reproduction, towards MAT1-1 and MAT1-2, respectively. The implications of these findings and future research directions for improved understanding of P. biglobosus epidemiology on OSR, particularly in China, are considered.