受限于 GNN 的时空复杂度和 large-scale 图数据的挑战,本文首先提出了一种二值图卷积网络 (Binary Graph Convolutional Network, Bi-GCN),Bi-GCN 将网络参数和输入节点特征二值化并且将原始 GNN 操作的矩阵乘法修改为计算效率更高的二值运算。基于理论分析,Bi-GCN 可以将网络参数和输入数据的内存
To deal with the issue, in this paper, we introduce two novel progressive binary graph convolutional network for skeleton-based action recognition PB-GCN and PB-GCN*, which can obtain significant speed-up and memory saving. In PB-GCN, the filters are binarized, and in PB-GCN*, both ...
Graph Convolutional Network (GCN) is proposed to model multi-relational image and generate more informative image representations. Recently, the relations between medical images are utilized to identify diseases. This paper proposes a Gated GCN with Attention Convolutional Binary Neural Tree (GGAC) for ...
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. In: Advances in Neural Information Proce...
Improving cross-platform binary analysis using representation learning via graph alignment ISSTA 2022 link link link jTrans: Jump-Aware Transformer for Binary Code Similarity ISSTA 2022 link link link COBRA-GCN: Contrastive Learning to Optimize Binary Representation Analysis with Graph Convolutional Networks...
Sankar, A., Zhang, X., Chang, K.C.-C.: Motif-based convolutional neural network on graphs.arXiv:1711.05697(2017) Shen-Orr, S.S., Milo, R., Mangan, S., Alon, U.: Network motifs in the transcriptional regulation network ofEscherichia coli. Nat. Genet.31(1), 64–68 (2002) ...
Improving cross-platform binary analysis using representation learning via graph alignment ISSTA 2022 link link link jTrans: Jump-Aware Transformer for Binary Code Similarity ISSTA 2022 link link link COBRA-GCN: Contrastive Learning to Optimize Binary Representation Analysis with Graph Convolutional Networks...
The graph-cut algorithm has shown to yield a solution well bounded with respect to the optimal value [24]. The authors also demonstrated that, with shallow mod- els an interleaved process of binary code inference and hash function learning allowed bit correction and improved the retrieval ...
It is found that the semi-supervised graph convolutional network model trained on the graph-structured data composed of the adjacency matrix constructed using continuous geochemical evidential layers and the feature matrix constructed using the binary geological, geophysical and geochemical evidential layers...
The 4-queens constraint network: (a) the constraint graph, (b) the minimal binary constraints, and (c) the minimal unary constraints (the domains). PROPOSITION 2.2 If (a, b)∈ Mij then ∃ t∈ sol(M) such that t[i] = a and t[j] = b. We should note here that finding a ...