Semi-supervised methods, which efficiently leverage a small amount of labeled data, have been widely used in the field of medical imaging. This paper proposes a multi-level prototype-based morphological perception model that leverages the consistency of pixel intensities in medical images to enhance overall and edge segmentation. Deep prototypes capture global morphology, while shallow prototypes focus on edge details. The prototype loss encourages the encoder to separate foreground and background features. This multi-scale pixel-level prototype consistency is utilized to supervise the model’s predictions on unlabeled data, enabling better utilization of the unlabeled data. Additionally, we observed that this consistency constraint may cause the encoder to lose detailed features. To address this, we designed a sparse multi-scale attention module that accelerates the recovery of detailed information by fusing global and local information from other layers. We conducted comparative validation against other semi-supervised methods on well-known public medical segmentation datasets.

Solving partial differential equations (PDEs) by numerical methods meet computational cost challenge for getting the accurate solution since fine grids and small time steps are required. Machine learning can accelerate this process, but struggle with weak generalizability, interpretability, and data dependency, as well as suffer in long-term prediction. To this end, we propose a PDE-embedded network with multiscale time stepping (MultiPDENet), which fuses the scheme of numerical methods and machine learning, for accelerated simulation of flows. In particular, we design a convolutional filter based on the structure of finite difference stencils with a small number of parameters to optimize, which estimates the equivalent form of spatial derivative on a coarse grid to minimize the equation's residual. A Physics Block with a 4th-order Runge-Kutta integrator at the fine time scale is established that embeds the structure of PDEs to guide the prediction. To alleviate the curse of temporal error accumulation in long-term prediction, we introduce a multiscale time integration approach, where a neural network is used to correct the prediction error at a coarse time scale. Experiments across various PDE systems, including the Navier-Stokes equations, demonstrate that MultiPDENet can accurately predict long-term spatiotemporal dynamics, even given small and incomplete training data, e.g., spatiotemporally down-sampled datasets. MultiPDENet achieves the state-of-the-art performance compared with other neural baseline models, also with clear speedup compared to classical numerical methods

We study the multi-armed bandit (MAB) problem with composite and anonymous feedback. In this model, the reward of pulling an arm spreads over a period of time (we call this period as reward interval) and the player receives partial rewards of the action, convoluted with rewards from pulling other arms, successively. Existing results on this model require prior knowledge about the reward interval size as an input to their algorithms. In this paper, we propose adaptive algorithms for both the stochastic and the adversarial cases, without requiring any prior information about the reward interval. For the stochastic case, we prove that our algorithm guarantees a regret that matches the lower bounds (in order). For the adversarial case, we propose the first algorithm to jointly handle non-oblivious adversary and unknown reward interval size. We also conduct simulations based on real-world dataset. The results show that our algorithms outperform existing benchmarks.

Multivariate Hawkes processes are commonly used to model streaming networked event data in a wide variety of applications. However, it remains a challenge to extract reliable inference from complex datasets with uncertainty quantification. Aiming towards this, we develop a statistical inference framework to learn causal relationships between nodes from networked data, where the underlying directed graph implies Granger causality. We provide uncertainty quantification for the maximum likelihood estimate of the network multivariate Hawkes process by providing a non-asymptotic confidence set. The main technique is based on the concentration inequalities of continuous-time martingales. We compare our method to the previously-derived asymptotic Hawkes process confidence interval, and demonstrate the strengths of our method in an application to neuronal connectivity reconstruction.

Establishing high-quality correspondence maps between geometric shapes has been shown to be the fundamental problem in managing geometric shape collections. Prior work has focused on computing efficient maps between pairs of shapes, and has shown a quantifiable benefit of joint map synchronization, where a collection of shapes are used to improve (denoise) the pairwise maps for consistency and correctness. However, these existing map synchronization techniques place very strong assumptions on the input shapes collection such as all the input shapes fall into the same category and/or the majority of the input pairwise maps are correct. In this paper, we present a multiple map synchronization approach that takes a heterogeneous shape collection as input and simultaneously outputs consistent dense pairwise shape maps. We achieve our goal by using a novel tensor-based representation for map synchronization, which is efficient and robust than all prior matrix-based representations. We demonstrate the usefulness of this approach across a wide range of geometric shape datasets and the applications in shape clustering and shape co-segmentation.

The network I/O operations of a guest domain spend Domain0's processor resource as well as its own processor resource. If no control is placed on the network I/O operations of guest domains, Xen system will likely overload when executing network I/O-intensive workload. To resolve this problem, the allowable network I/O request number of Xen system should be firstly figured out. This paper illuminated the characteristic of Xen system in handling the network I/O operations of guest domains with two experimental results, and established several performance analyzing and predicting models by studying the network I/O procedure and the processor resource consumption distribution of Xen system. These models can compute the allowable number of guest domains with fixed network I/O request number or the allowable network I/O request number of each guest domain based on all idle processor resource of Xen system, and prevent Xen system from overloading. Finally, the applicability of these models is preliminarily analyzed.