Fully programmable valve array (FPVA) biochips have emerged as a next-generation platform for flow-based microfluidics, offering high flexibility and programmability for executing complex bioassays. However, physical faults such as channel blockage and leakage are inevitable during chip manufacturing and operation, and the widely adopted single-port architecture in existing research serializes fluid injection, severely limiting throughput and fault-tolerant routing quality under large-scale conditions. To address this challenge, this paper proposes MP-FTRouter, a fault-tolerant routing algorithm for multi-port FPVA using deep reinforcement learning. The proposed algorithm introduces a multi-port flow-layer architecture to alleviate the serialization bottleneck of single-port designs, and models the concurrent routing process as a Markov decision process. By combining value decomposition networks with double deep Q-networks, MP-FTRouter achieves conflict avoidance and path optimization under fault constraints through staged concurrent batch generation and multi-agent cooperative decision-making. Experimental results on large-scale benchmarks demonstrate that, compared with existing work, the proposed algorithm reduces the completion time of bioassays by an average of 40.6%, the total length of flow paths by an average of 47.8%, and improves the fault-tolerance success rate by 6%.

Traffic flow prediction is crucial to intelligent transportation systems (ITSs). However, the existing methods usually ignore the problem that the prediction difficulty of nodes in the traffic network is actually different. Besides, they fail to effectively handle the dilution of the original semantic information passed layer by layer when capturing the global dependency. To address these issues, this article proposes a curriculum learning guided spatial–temporal network (CurST-Net). Inspired by the human learning process, CurST-Net introduces a curriculum learning (CL) module that defines four metrics from multiple views to evaluate node difficulty and uses a training scheduler (TNS) to gradually introduce easy-to-difficult training nodes to the model to improve prediction ability. Moreover, we design a global spatial–temporal encoder that uses a multihead spatial–temporal attention mechanism and performs interlayer residual scaling on the original semantic information to efficiently capture the global spatial–temporal correlation of nodes. To the best of our knowledge, this is the first work that uses CL to solve the varying prediction difficulty of nodes in traffic flow prediction. The effectiveness of our model is validated through extensive experiments with 12 baseline models on three real-world traffic datasets. For the 1-h prediction horizon, the MAE values of our model on the three datasets are 15.19, 19.22, and 15.50, respectively. Our method yields an overall reduction of 6.51% in MAE across all three datasets compared to DSTAGNN, an advanced traffic flow prediction method. Additionally, the inference time on the PEMSD8 dataset is 5.44 s, requiring only 45% of the inference time of DSTAGNN, which demonstrates a significant improvement in inference speed.

Despite significant progress in medical image segmentation, clinical deployment faces challenges due to inherent uncertainties. These uncertainties primarily arise from ambiguous lesion boundaries, complex anatomical structures, and variations in imaging quality, all of which significantly affect the reliability of segmentation outcomes. To address this issue, we propose a novel Hierarchical Uncertainty-Aware Segmentation Framework (HUA-Seg), which explicitly models and utilizes uncertainty throughout the forward propagation process. HUASeg is designed to hierarchically perceive, quantify, and exploit uncertainty, enhancing segmentation robustness and generalization. Our method comprises three core components: (1) an uncertainty-modulated self-attention mechanism that adaptively emphasizes reliable features during early-stage representation learning, enabling the extraction of more robust feature embeddings; (2) an uncertainty-guided dual-strategy feature refinement module, which reallocates learning focus towards low-confidence regions-such as lesion boundaries-facilitating effective complex example mining and contour refinement; and (3) multi-scale uncertainty supervision, providing an explicit, data-dependent regularization signal that stabilizes training and enhances generalization. Extensive experiments on multiple public medical image segmentation benchmarks demonstrate that HUA-Seg consistently outperforms state-of-the-art methods, highlighting its effectiveness in handling complex and uncertain medical image segmentation scenarios.

Witnessing the advancements in the scale and complexity of chip design, along with the benefits from high-performance computing technologies, the simulation of Very Large Scale Integration (VLSI) circuits increasingly demands acceleration through parallel computing with GPU devices. However, conventional parallel strategies fail to fully leverage modern GPU capabilities, introducing new challenges in GPU-based parallelism for VLSI simulations despite previous demonstrations of significant acceleration. In this paper, we propose a novel approach for accelerating the simulation of 4-value logic timing-aware gate-level circuits through waveform-based GPU parallelism. Our approach introduces an innovative strategy that effectively manages task dependencies during the parallelism of combinational circuits, significantly reducing the synchronization requirement between CPU and GPU. The proposed approach achieves one-pass parallelism by requiring only a single round of data transfer. Moreover, to address the implementation challenges associated with our strategy on GPU devices, we have developed and optimized a series of data structures that dynamically allocate and store newly generated outputs of uncertain scale. Finally, we conduct experiments on industrial-scale open-source benchmarks to demonstrate our approach’s performance gains over several state-of-the-art baselines.

Graph neural networks (GNNs) are widely used for analyzing graph-structural data and solving graph-related tasks due to their powerful expressiveness. However, existing off-the-shelf GNN-based models usually consist of no more than three layers. Deeper GNNs usually suffer from severe performance degradation due to several issues including the infamous "over-smoothing" issue, which restricts the further development of GNNs. In this article, we investigate the over-smoothing issue in deep GNNs. We discover that over-smoothing not only results in indistinguishable embeddings of graph nodes, but also alters and even corrupts their semantic structures, dubbed semantic over-smoothing. Existing techniques, e.g., graph normalization, aim at handling the former concern, but neglect the importance of preserving the semantic structures in the spatial domain, which hinders the further improvement of model performance. To alleviate the concern, we propose a cluster-keeping sparse aggregation strategy to preserve the semantic structure of embeddings in deep GNNs (especially for spatial GNNs). Particularly, our strategy heuristically redistributes the extent of aggregations for all the nodes from layers, instead of aggregating them equally, so that it enables aggregate concise yet meaningful information for deep layers. Without any bells and whistles, it can be easily implemented as a plug-and-play structure of GNNs via weighted residual connections. Last, we analyze the over-smoothing issue on the GNNs with weighted residual structures and conduct experiments to demonstrate the performance comparable to the state-of-the-arts.

Despite Graph neural networks' significant performance gain over many classic techniques in various graph-related downstream tasks, their successes are restricted in shallow models due to over-smoothness and the difficulties of optimizations among many other issues. In this paper, to alleviate the over-smoothing issue, we propose a soft graph normalization method to preserve the diversities of node embeddings and prevent indiscrimination due to possible over-closeness. Combined with residual connections, we analyze the reason why the method can effectively capture the knowledge in both input graph structures and node features even with deep networks. Additionally, inspired by Curriculum Learning that learns easy examples before the hard ones, we propose a novel label-smoothing-based learning framework to enhance the optimization of deep GNNs, which iteratively smooths labels in an auxiliary graph and constructs many gradual non-smooth tasks for extracting increasingly complex knowledge and gradually discriminating nodes from coarse to fine. The method arguably reduces the risk of overfitting and generalizes better results. Finally, extensive experiments are carried out to demonstrate the effectiveness and potential of the proposed model and learning framework through comparison with twelve existing baselines including the state-of-the-art methods on twelve real-world node classification benchmarks.

Recent studies have shown that Graph Transformers (GTs) can be effective for specific graph-level tasks. However, when it comes to node classification, training GTs remains challenging, especially in semi-supervised settings with a severe scarcity of labeled data. Our paper aims to address this research gap by focusing on semi-supervised node classification. To accomplish this, we develop a curriculum-enhanced attention distillation method that involves utilizing a Local GT teacher and a Global GT student. Additionally, we introduce the concepts of in-class and out-of-class and then propose two improvements, out-of-class entropy and top-k pruning, to facilitate the student's out-of-class exploration under the teacher's in-class guidance. Taking inspiration from human learning, our method involves a curriculum mechanism for distillation that initially provides strict guidance to the student and gradually allows for more out-of-class exploration by a dynamic balance. Extensive experiments show that our method outperforms many state-of-the-art approaches on seven public graph benchmarks, proving its effectiveness.

Abstract Knowledge graph (KG) has been fully considered in natural language generation (NLG) tasks. A KG can help models generate controllable text and achieve better performance. However, most existing related approaches still lack explainability and scalability in large‐scale knowledge reasoning. In this work, we propose a novel CogNLG framework for KG‐to‐text generation tasks. Our CogNLG is implemented based on the dual‐process theory in cognitive science. It consists of two systems: one system acts as the analytic system for knowledge extraction, and another is the perceptual system for text generation by using existing knowledge. During text generation, CogNLG provides a visible and explainable reasoning path. Our framework shows excellent performance on all datasets and achieves a BLEU score of 36.7, which increases by 6.7 compared to the best competitor.

Incorporating differentially private continuous data release (DPCR) into private federated learning (FL) has recently emerged as a powerful technique for enhancing accuracy. Designing an effective DPCR model is the key to improving accuracy. Still, the state-of-the-art DPCR models hinder the potential for accuracy improvement due to insufficient privacy budget allocation and the design only for specific iteration numbers. To boost accuracy further, we develop an augmented BIT-based continuous data release (AuBCR) model, leading to demonstrable accuracy enhancements. By employing a dual-release strategy, AuBCR gains the potential to further improve accuracy, while confronting the challenge of consistent release and doubly-nested complex privacy budget allocation problem. Against this, we design an efficient optimal consistent estimation algorithm with only$O(1)$complexity per release. Subsequently, we introduce the$(k, N)$-AuBCR Model concept and design a meta-factor method. This innovation significantly reduces the optimization variables from$O(T)$to$O\left ({{lg^{2} T}}\right)$, thereby greatly enhancing the solvability of optimal privacy budget allocation and simultaneously supporting arbitrary iteration number T. Our experiments on classical datasets show that AuBCR boosts accuracy by 4.9% ~ 18.1% compared to traditional private FL and 0.4% ~ 1.2% compared to the state-of-the-art ABCRG model.

Achieving good performance on few-shot or zero-shot datasets has been a long-term challenge for NER. The conventional semantic transfer approaches on NER will decrease model performance when the semantic distribution is quite different, especially in Chinese few-shot NER. Recently, prompt-tuning has been thoroughly considered for low-resource tasks. But there is no effective prompt-tuning approach for Chinese few-shot NER. In this work, we propose a prompt-based Parent and Child BERT (PCBERT) for Chinese few-shot NER. To train an annotating model on high-resource datasets and then discover more implicit labels on low-resource datasets. We further design a label extension strategy to achieve label transferring from high-resource datasets. We evaluated our model on Weibo and the other three sampling Chinese NER datasets, and the experimental result demonstrates our approach’s effectiveness in few-shot learning.