Dezhong Yao

With the rise of Web 2.0 and microservices, the increasing availability of Web APIs has intensified the need for effective recommendation systems. Existing approaches are generally categorized into two methods: recommendation-type methods, which classify APIs using labels, and match-type methods, which retrieve APIs through matching with mashups. However, three significant challenges remain: 1) semantic ambiguities in comparing API and mashup descriptions, 2) a lack of progressive semantic refinement between the mashup requirements and the individual API descriptions, and 3) computational inefficiency of exhaustive mashup-API comparisons in large-scale repositories. To tackle these challenges, we propose WARBERT, a hierarchical model based on BERT for Web API recommendation. WARBERT utilizes dual-component feature fusion and attention mechanisms to create accurate semantic representations. It consists of WARBERT(R) for initial candidate filtering using recommendation methods, and WARBERT(M), which focuses on refined similarity matching. The final likelihood of an API-mashup pairing combines predictions from both components, with WARBERT(R) further enhanced by an auxiliary task of predicting mashup categories. Experiments conducted on the ProgrammableWeb dataset demonstrate that WARBERT outperforms existing baselines, achieving notable improvements in both accuracy and efficiency.

With the development of cloud computing, the number of Web APIs has increased dramatically, further intensifying the demand for efficient Web API recommendation. Despite the demonstrated success of previous Web API recommendation solutions, two critical challenges persist: 1) a fixed top-N recommendation that cannot accommodate the varying API cardinality requirements of different mashups, and 2) these methods output only ranked API lists without accompanying reasons, depriving users of understanding the recommendation. To address these challenges, we propose WAR-Re, an LLM-based model for Web API recommendation with semantic reasoning for justification. WAR-Re leverages special start and stop tokens to handle the first challenge and uses two-stage training: supervised fine-tuning and reinforcement learning via Group Relative Policy Optimization (GRPO) to enhance the model's ability in both tasks. Comprehensive experimental evaluations on the ProgrammableWeb dataset demonstrate that WAR-Re achieves a gain of up to 21.59\% over the state-of-the-art baseline model in recommendation accuracy, while consistently producing high-quality semantic reasons for recommendations.

Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstrated the vulnerability of deep hashing models to backdoor attacks. Although these studies have shown promising attack results, they rely on access to the training dataset to implant the backdoor. In the real world, obtaining such data (e.g., identity information) is often prohibited due to privacy protection and intellectual property concerns. Embedding backdoors into deep hashing models without access to the training data, while maintaining retrieval accuracy for the original task, presents a novel and challenging problem. In this paper, we propose DarkHash, the first data-free backdoor attack against deep hashing. Specifically, we design a novel shadow backdoor attack framework with dual-semantic guidance. It embeds backdoor functionality and maintains original retrieval accuracy by fine-tuning only specific layers of the victim model using a surrogate dataset. We consider leveraging the relationship between individual samples and their neighbors to enhance backdoor attacks during training. By designing a topological alignment loss, we optimize both individual and neighboring poisoned samples toward the target sample, further enhancing the attack capability. Experimental results on four image datasets, five model architectures, and two hashing methods demonstrate the high effectiveness of DarkHash, outperforming existing state-of-the-art backdoor attack methods. Defense experiments show that DarkHash can withstand existing mainstream backdoor defense methods.

Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstrated the vulnerability of deep hashing models to backdoor attacks. Although these studies have shown promising attack results, they rely on access to the training dataset to implant the backdoor. In the real world, obtaining such data (e.g., identity information) is often prohibited due to privacy protection and intellectual property concerns. Embedding backdoors into deep hashing models without access to the training data, while maintaining retrieval accuracy for the original task, presents a novel and challenging problem. In this paper, we propose DarkHash, the first data-free backdoor attack against deep hashing. Specifically, we design a novel shadow backdoor attack framework with dual-semantic guidance. It embeds backdoor functionality and maintains original retrieval accuracy by fine-tuning only specific layers of the victim model using a surrogate dataset. We consider leveraging the relationship between individual samples and their neighbors to enhance backdoor attacks during training. By designing a topological alignment loss, we optimize both individual and neighboring poisoned samples toward the target sample, further enhancing the attack capability. Experimental results on four image datasets, five model architectures, and two hashing methods demonstrate the high effectiveness of DarkHash, outperforming existing state-of-the-art backdoor attack methods. Defense experiments show that DarkHash can withstand existing mainstream backdoor defense methods.

Cerebral ischemia restricts cerebral blood flow (CBF), leading to unstable hemodynamics. Past studies of ischemia mainly focused on cortical CBF reduction. However, its impact on hemodynamic changes, especially temporal varying characteristics, remains poorly understood. Here, we collected cortical resting-state CBF in rats with left carotid artery blockage during occlusion-reperfusion, and measured the temporal variability and changes in laterality using a novel state-space method. This method was also applied to stroke EEG datasets to validate its effectiveness. After arterial occlusion, the left marginal motor, sensory, auditory, and visual cortices exhibited severe temporal variability impairments. The laterality analysis indicated that affected left regions showed inferior unilateral mean, inter-hemispheric transition probability, time fraction, and laterality duration, while the right side had a higher laterality time fraction and duration. These impairments recovered partially following blood flow restoration. Besides, the ischemic state-space metrics were positively correlated with the pre-occlusion baseline appearance. Stroke patients exhibited impaired temporal variability in the affected ischemic hemisphere. The state-space analysis revealed damaged CBF temporal variability during cerebral ischemia and predicted baseline-ischemia connections.

The Sparse General Matrix-Matrix multiplication (SpGEMM) is a fundamental component for many applications, such as algebraic multigrid methods (AMG), graphic processing, and deep learning. However, the unbearable latency of computing high-dimensional, large-scale sparse matrix multiplication on GPUs hinders the development of these applications. An effective approach is heterogeneous cores collaborative computing, but this method must address three aspects: (1) irregular non-zero elements lead to load imbalance and irregular memory access, (2) different core computing latency differences reduce computational parallelism, and (3) temporary data transfer between different cores introduces additional latency overhead. In this work, we propose an innovative framework for collaborative large-scale sparse matrix multiplication on CPU-GPU heterogeneous cores, named ApSpGEMM. ApSpGEMM is based on sparsity rules and proposes reordering and splitting algorithms to eliminate the impact of non-zero element distribution features on load and memory access. Then adaptive panels allocation with affinity constraints among cores improves computational parallelism. Finally, carefully arranged asynchronous data transmission and computation balance communication overhead. Compared with state-of-the-art SpGEMM methods, our approach provides excellent absolute performance on matrices with different sparse structures. On heterogeneous cores, the GFlops of large-scale sparse matrix multiplication is improved by 2.25 to 7.21 times.