Multi-view clustering, which elegantly integrates information from multiple sources to reveal the intrinsic structure among data, is attracting increasing attention in the field of machine learning. Although good performance has been achieved by the existing methods, we observe that they have neglected the inherent local structure between the base kernels. This may cause adverse effects on clustering performance. In this paper, we propose a simple but effective late fusion multiple kernel clustering with local kernel alignment maximization algorithm (LF-MKC-LKA) to address the issue. Specifically, we first search the neighbors for each sample by finding the nearest k neighbors in the average kernel space and then get neighbor indicator matrix for each sample. With the help of neighbor indicator matrix, the local kernels for each view can be constructed subsequently, which preserve only the high-confidence local similarities for learning the intrinsic global manifold of data. Moreover, they can be used to preserve the block diagonal structure and boost the robustness against noise between the base kernels. We input the local kernels of each view into the kernel $k$ -means (KKM) algorithm and get the local basic partitions. Finally, we use the local basic partitions as late fusion input to design a three-step iterative algorithm. As demonstrated, the proposed LF-MKC-LKA is proved to be effective and efficient by a large number of experiments on $11$ multi-kernel benchmark datasets. A series of experiments are also designed to prove the fast convergence, excellent performance, robustness and low parameter sensitivity of the algorithm.

Routing algorithms for cache-coherent NoCs only have limited VCs at their disposal, which poses challenges to the design of routing algorithms. Existing fully adaptive routing algorithms apply conservative VC re-allocation: only empty VCs can be re-allocated, which limits performance. We propose two novel flow control designs. First, whole packet forwarding (WPF) re-allocates a nonempty VC if the VC has enough free buffers for an entire packet. WPF does not induce deadlock if the routing algorithm is deadlock-free using conservative VC re-allocation. It is an important extension to several deadlock avoidance theories. Second, we extend Duato's theory to apply aggressive VC re-allocation on escape VCs without deadlock. Finally, we propose a design which maintains maximal routing flexibility with low hardware cost. For synthetic traffic, our design performs averagely 88.9 percent better than existing fully adaptive routing. Our design is superior to partially adaptive and deterministic routing.

Deep learning has achieved outstanding results in various tasks in machine learning under the background of rapid increase in equipment’s computing capacity. However, while achieving higher performance and effects, model size is larger, training and inference time longer, the memory and storage occupancy increasing, the computing efficiency shrinking, and the energy consumption augmenting. Consequently, it’s difficult to let these models run on edge devices such as micro and mobile devices. Model compression technology is gradually emerging and researched, for instance, model quantization. Quantization aware training can take more accuracy loss resulting from data mapping in model training into account, which clamps and approximates the data when updating parameters, and introduces quantization errors into the model loss function. In quantization, we found that some stages of the two super-resolution model networks, SRGAN and ESRGAN, showed sensitivity to quantization, which greatly reduced the performance. Therefore, we use higher-bits integer quantization for the sensitive stage, and train the model together in quantization aware training. Although model size was sacrificed a little, the accuracy approaching the original model was achieved. The ESRGAN model was still reduced by nearly 67.14% and SRGAN model was reduced by nearly 68.48%, and the inference time was reduced by nearly 30.48% and 39.85% respectively. What’s more, the PI values of SRGAN and ESRGAN are 2.1049 and 2.2075 respectively.

Simulating the behavior of quantum circuits on classical computers are one of the widely used approaches for current quantum computing device and quantum algorithm research. State-vector simulators keep all the quantum states in main memory, thus consuming a large amount of memory and resulting in great memory access and communication overhead far longer than calculation time. Many classical simulators, such as QuEST, are designed by serial execution of quantum gates without using the data locality, and all amplitudes need to be exchanged. Such a gate-unaware full data communication scheme forces powerful computation such as GPUs to spend a lot of time on waiting for data transmission. In this paper, we propose a gate-aware on-demand communication quantum simulation framework to optimize communication overhead. A quantum circuit partition method through gate fusion is first proposed to avoid unnecessary communications. Moreover, a on-demand data communication scheme is proposed to optimize data transfer among computation nodes. Based on these designs, a prototype has been implemented on QuEST. We evaluated on an 8-node cluster with four NVIDIA Tesla V100 GPUs on each node and our designs can achieve 3.0x-15.6x speedup compared to QuEST for 32-34-qubit quantum systems. Moverover, it can scale to simulate 37-qubit quantum system instead of 34-qubit quantum system for QuEST.

The misalignment between classification and localization is a significant performance improvement point for object detection. To cope with the misalignment problem, more attempts have been made to separate different tasks (e.g., Classification, Bounding Box Regression) by introducing extra heads, which emphasizes the separation of multiple tasks to cope with their variability. In this paper, we consider that both separation and crosstalk are important between classification and localization. Considering that the two types of tasks are different and have different regions and features of interest, they are in conflict with each other and therefore need to be separated. However, they also need to be fused, because classification and localization are, after all, about understanding the same object. To realize this idea, we introduce bidirectional crosstalk detection head in a systematic manner to provide a full deep cross-fusion between classification and localization. To our best knowledge, it is the first time that full bidirectional crosstalk is introduced between classification and localization for one-stage detector. Extensive experiments are conducted to demonstrate the effectiveness of the proposed method. With a ResNet-50 backbone, our method can significantly improve the GFLV1 baseline by 2.0 AP with similar inference speed (18.5 fps vs. 18.3 fps) and further boost GFLV1 with a big margin (4.3 AP) by increasing our model size. Fair comparisons also show that the proposed head outperforms state-of-the-art heads (T-Head, DyHead) with comparable or faster inference speed under the same ATSS baseline model. With a Res2Net-DCN backbone, our model achieves 51.7 AP at single-model single-scale testing. The code and pretrained models will be made publicly available.