Search

Graph neural networks (GNNs) have demonstrated superior performance in various tasks on graphs. However, existing GNNs often suffer from weak-generalization due to sparsely labeled datasets. Here we propose a novel framework that learns to augment the input features using topological information and automatically controls the strength of augmentation. Our framework learns the augmentor to minimize GNNs’ loss on unseen labeled data while maximizing the consistency of GNNs’ predictions on unlabeled data. This can be formulated as a meta-learning problem and our framework alternately optimizes the augmentor and GNNs for a target task. Our extensive experiments demonstrate that the proposed framework is applicable to any GNNs and significantly improves the performance of graph neural networks on node classification. In particular, our method provides 5.78% improvement with Graph convolutional network (GCN) on average across five benchmark datasets.

Graph neural networks have shown promising results on representing and analyzing diverse graph-structured data, such as social networks, traffic flow, drug discovery, and recommendation systems. Existing approaches for graph neural networks typically suffer from the oversmoothing issue that results in indistinguishable node representation, as recursive and simultaneous neighborhood aggregation deepens. Also, most methods focus on transductive scenarios that are limited to fixed graphs, which do not generalize properly to unseen graphs. To address these issues, we propose a novel graph neural network that considers both edge-based neighborhood relationships and node-based entity features with multiple steps, i.e. Graph Entities with Step Mixture via random walk (GESM). GESM employs a mixture of various steps through random walk to alleviate the oversmoothing problem, an attention mechanism to dynamically reflect interrelations depending on node information, and structure-based regularization to enhance embedding representation. With intensive experiments, we show that our proposed GESM achieves state-of-the-art or comparable performances on eight benchmark graph datasets in both transductive and inductive learning tasks. Furthermore, we empirically demonstrate the superiority of our method on the oversmoothing issue with rich graph representations. Our source code is available at https://github.com/ShinKyuY/GESM.

Filter pruning is prevalent for pruning-based model compression. Most filter pruning methods have two main issues: 1) the pruned network capability depends on that of source pretrained models, and 2) they do not consider that filter weights follow a normal distribution. To address these issues, we propose a new pruning method employing both weight re-initialization and latent space clustering. For latent space clustering, we define filters and their feature maps as vertices and edges to be a graph, transformed into a latent space by graph convolution, alleviating to prune zero-near weight filters only. In addition, a part of filters is re-initialized with a constraint for enhancing filter diversity, and thus the pruned model is less dependent on the source network. This approach provides more robust accuracy even when pruned from the pretrained model with low accuracy. Extensive experimental results show our method decreases 56.6% and 84.6% of FLOPs and parameters of VGG16 with negligible loss of accuracy on CIFAR100, which is the state-of-the art performance. Furthermore, our method presents outperforming or comparable pruning results against state-of-the-art models on multiple datasets.

Abstract Background Indigenous cattle in Africa have adapted to various local environments to acquire superior phenotypes that enhance their survival under harsh conditions. While many studies investigated the adaptation of overall African cattle, genetic characteristics of each breed have been poorly studied. Results We performed the comparative genome-wide analysis to assess evidence for subspeciation within species at the genetic level in trypanotolerant N’Dama cattle. We analysed genetic variation patterns in N’Dama from the genomes of 101 cattle breeds including 48 samples of five indigenous African cattle breeds and 53 samples of various commercial breeds. Analysis of SNP variances between cattle breeds using wMI, XP-CLR, and XP-EHH detected genes containing N’Dama-specific genetic variants and their potential associations. Functional annotation analysis revealed that these genes are associated with ossification, neurological and immune system. Particularly, the genes involved in bone formation indicate that local adaptation of N’Dama may engage in skeletal growth as well as immune systems. Conclusions Our results imply that N’Dama might have acquired distinct genotypes associated with growth and regulation of regional diseases including trypanosomiasis. Moreover, this study offers significant insights into identifying genetic signatures for natural and artificial selection of diverse African cattle breeds.