Temporal Knowledge GraphKnowledge Graphs (KGs), as a collection of human knowledge, have shown great prospects in natural language processing, recommendation systems and information retrieval. The tra
IntroductionIn this repo, we choose the domain of COVID-19 and deep learning to predict the trends of the science of science. We use the information of papers and fields from Acemap. It is worth noti
IntroductionContrastive learning is a self-supervised learning method to learn representations by contrasting positive and negative examples. For self-supervised contrastive learning, the next equatio
IntroductionIn this article, I implemented some variants of DCGAN[1], which is one of the generative adversarial networks. The DCGAN model has replaced the fully connected layer with the global poolin
Paper: Wang, Xingbin, et al. “Dnnguard: An elastic heterogeneous dnn accelerator architecture against adversarial attacks.” Proceedings of the Twenty-Fifth International Conference on Architectural S
Paper: Abts, Dennis, et al. “Think fast: a tensor streaming processor (TSP) for accelerating deep learning workloads.” 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA
IntroductionThe von Neumann graph entropy (VNGE) facilitates measurement of information divergence and distance between graphs in a graph sequence. Given an undirected graph G=(V, E, A), where A is t
Paper: Ham, Tae Jun, et al. “A^ 3: Accelerating Attention Mechanisms in Neural Networks with Approximation.” 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE,
Paper: Liu, Hongyuan, Sreepathi Pai, and Adwait Jog. “Why GPUs are slow at executing NFAs and how to make them faster.” Proceedings of the Twenty-Fifth International Conference on Architectural Suppo
DeepFakeImagine if someone replaces the character in a certain video with your face image just for fun, what would you think? This is what DeepFake is doing. Its function is to combine and superimpose