Advanced artificial intelligence techniques, such as federated learning, has been applied to broad areas, e.g., image classification, speech recognition, smart city, and healthcare. Despite intensive research on federated learning, existing schemes are vulnerable to attacks and can hardly meet the security requirements for real-world applications. The problem of designing a secure federated learning framework to ensure the correctness of training procedure has not been sufficiently studied and remains open. In this paper, we propose VFChain, a verifiable and auditable federated learning framework based on the blockchain system. First, to provide the verifiability, a committee is selected through the blockchain to collectively aggregate models and record verifiable proofs in the blockchain. Then, to provide the auditability, a novel authenticated data structure is proposed for blockchain to improve the search efficiency of verifiable proofs and support a secure rotation of committee. Finally, to further improve the search efficiency, an optimization scheme is proposed to support multiple-model learning tasks. We implement VFChain and conduct extensive experiments by utilizing the popular deep learning models over the public real-world dataset. The evaluation results demonstrate the effectiveness of our proposed VFChain system.

Recently, federated learning (FL) techniques have enabled multiple users to train machine learning models collaboratively without data sharing. However, existing FL algorithms suffer from the communication bottleneck due to network bandwidth pressure and/or low bandwidth utilization of the participating clients in both centralized and decentralized architectures. To deal with the communication problem while preserving the convergence performance, we introduce a communication-efficient decentralized FL framework GossipFL. In GossipFL, we 1) design a novel sparsification algorithm to enable that each client only needs to communicate with one peer with a highly sparsified model, and 2) propose a new and novel gossip matrix generation algorithm that can better utilize the bandwidth resources while preserving the convergence property. We also theoretically prove that GossipFL has convergence guarantees. We conduct experiments with three convolutional neural networks on two datasets (IID and non-IID) under two distributed environments (14 clients and 100 clients) to verify the effectiveness of GossipFL. Experimental results show that GossipFL takes less communication traffic for 38.5% and less communication time for $49.8$ % than state-of-the-art solutions while achieving comparative model accuracy.

Memory access efficiency is a key factor in fully utilizing the computational power of graphics processing units (GPUs). However, many details of the GPU memory hierarchy are not released by GPU vendors. In this paper, we propose a novel fine-grained microbenchmarking approach and apply it to three generations of NVIDIA GPUs, namely Fermi, Kepler, and Maxwell, to expose the previously unknown characteristics of their memory hierarchies. Specifically, we investigate the structures of different GPU cache systems, such as the data cache, the texture cache and the translation look-aside buffer (TLB). We also investigate the throughput and access latency of GPU global memory and shared memory. Our microbenchmark results offer a better understanding of the mysterious GPU memory hierarchy, which will facilitate the software optimization and modelling of GPU architectures. To the best of our knowledge, this is the first study to reveal the cache properties of Kepler and Maxwell GPUs, and the superiority of Maxwell in shared memory performance under bank conflict.

Motivation: Since 1990, the basic local alignment search tool (BLAST) has become one of the most popular and fundamental bioinformatics tools for sequence similarity searching, receiving extensive attention from the research community. The two pioneering papers on BLAST have received over 96 000 citations. Given the huge population of BLAST users and the increasing size of sequence databases, an urgent topic of study is how to improve the speed. Recently, graphics processing units (GPUs) have been widely used as low-cost, high-performance computing platforms. The existing GPU-BLAST is a promising software tool that uses a GPU to accelerate protein sequence alignment. Unfortunately, there is still no GPU-accelerated software tool for BLAST-based nucleotide sequence alignment. Results: We developed G-BLASTN, a GPU-accelerated nucleotide alignment tool based on the widely used NCBI-BLAST. G-BLASTN can produce exactly the same results as NCBI-BLAST, and it has very similar user commands. Compared with the sequential NCBI-BLAST, G-BLASTN can achieve an overall speedup of 14.80X under ‘megablast’ mode. More impressively, it achieves an overall speedup of 7.15X over the multithreaded NCBI-BLAST running on 4 CPU cores. When running under ‘blastn’ mode, the overall speedups are 4.32X (against 1-core) and 1.56X (against 4-core). G-BLASTN also supports a pipeline mode that further improves the overall performance by up to 44% when handling a batch of queries as a whole. Currently G-BLASTN is best optimized for databases with long sequences. We plan to optimize its performance on short database sequences in our future work. Availability:http://www.comp.hkbu.edu.hk/∼chxw/software/G-BLASTN.html Contact:chxw@comp.hkbu.edu.hk Supplementary information: Supplementary data are available at Bioinformatics online.

Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step. Existing methods use hand-designed propagation paths, ignoring the correlation between the entities and the query relation. In addition, the number of involved entities will explosively grow at larger propagation steps. In this work, we are motivated to learn an adaptive propagation path in order to filter out irrelevant entities while preserving promising targets. First, we design an incremental sampling mechanism where the nearby targets and layer-wise connections can be preserved with linear complexity. Second, we design a learning-based sampling distribution to identify the semantically related entities. Extensive experiments show that our method is powerful, efficient and semantic-aware. The code is available at https://github.com/LARS-research/AdaProp.