Home Most Read
Most Read
  • Jian Gao, Jiwu Shu
    Journal of Computer Research and Development. 2026, 63(3): 585-596. doi:10.7544/issn1000-1239.202550361

    Distributed lock is a crucial component in distributed storage systems. The performance of the lock protocol significantly influences the overall performance of the entire system. Remote direct memory access (RDMA) is an emerging data center networking technology that supports one-sided communication verbs and offers low CPU overhead, low latency, and high throughput. It presents new opportunities for designing high-performance distributed lock protocols. However, designing such RDMA based network protocols faces significant challenges, for example scalability and fairness. We address these challenges by proposing FeLock, an RDMA-based distributed lock protocol. FeLock achieves high performance while tackling the above challenges by leveraging different RDMA communication verbs, which enables the clients to communicate directly with both the server for lock acquisition and release, and other clients to hand over lock ownership. Specifically, first, to improve performance, FeLock introduces a per-node lock management mechanism to reduce network roundtrips on the critical paths of the lock protocol. Second, to achieve scalability, FeLock incorporates a round-robin handover mechanism, in which nodes are logically organized into a ring, and clients hand over lock ownership sequentially according to their positions within the ring. Third, to ensure fairness and prevent clients from starvation, FeLock employs a node credit mechanism that limits the number of consecutive lock acquisitions by any single node, thereby preventing clients on any node from being indefinitely blocked by others. Experimental results demonstrate that FeLock achieves performance comparable to or exceeding that of existing one-sided RDMA lock protocols, such as DSLR, while exhibiting better fairness and scalability. With 3 to 120 clients, FeLock achieves throughput 1.01 to 7.51 times of DSLR, with its fairness improved by up to 2.24 times.

  • Shunjie Wang, Guoyong Cai, Guangrui Lü
    Journal of Computer Research and Development. 2026, 63(2): 305-323. doi:10.7544/issn1000-1239.202440896

    Multimodal emotion recognition in conversations (MERC) has emerged as a prominent research focus in the domain of human-computer intelligent interaction. It demonstrates extensive applicability across diverse scenarios, including affective dialogue systems and conversational recommendation systems, thereby substantially improving user’s experience through enhanced emotional engagement. Identifying abstract emotional semantics in multimodal conversation scenarios poses a significant challenge. Current research predominantly relies on contrastive learning frameworks to extract discriminative feature. Although these approaches effectively enforce intra-class feature consistency, they inherently constrain fine-grained feature diversity. This limitation consequently impairs the model’s generalization capacity, particularly when processing samples from minority classes. In addition, current dialogue context graph learning only captures the dependence with a fixed window, neglecting the dynamic cross-correlation of the conversation flow, which can lead to either redundancy or insufficient of extracted context information. To address the aforementioned limitations, the adversarial soft-contrast modulated dynamic graph learning is proposed for MERC. Specifically, a dynamic discourse graph is firstly constructed according to the number of utterances emitted by the speaker in the conversation, which allows for dynamically modeling the conversational dependency range of the utterance in each modality to extract rich contextual information more precisely. Secondly, the adversarial soft-contrast training mechanism is designed to enhance the discrimination and robustness of the network learning. Among them, the class sample space is expanded by adding perturbations to the hidden layers of different modal feature extractors to generate adversarial samples, and the soft-contrast learning is exploited to maximize label semantic consistency of the original samples and the adversarial samples. Finally, a bi-stream graph learning strategy for different modalities is constructed, which not only explores the cross-modal consistent feature interaction guided by text semantics, but also learns the context dynamic dependencies within multimodal dialogue flow to collaboratively facilitates the complementary fusion of multimodal conversations data. Extensive experiments conducted on the IEMOCAP and MELD benchmark datasets have demonstrated that our proposed model achieves competitive results in terms of effectiveness for MERC, compared with current state-of-the-art methods.

  • Yaguan Qian, Qinqin Yu, Jiaqiang Sha, Qiqi Bao, Zhaoquan Gu, Shouling Ji, Bin Wang
    Journal of Computer Research and Development. 2026, 63(3): 752-767. doi:10.7544/issn1000-1239.202550024

    Deep neural networks (DNNs) have demonstrated remarkable success in numerous application areas, including computer vision, natural language processing, and speech recognition. However, recent studies have revealed that DNNs are vulnerable to adversarial attacks, particularly targeted attacks capable of precisely manipulating the outputs of unknown models, which poses significant risks to data privacy, model trustworthiness, and system security. Generative attack methods, which can efficiently create adversarial examples, have become a critical tool in advancing targeted attack techniques due to their ability to automate the generation process and reduce manual effort. Despite their potential, most existing generative attack approaches mainly focus on crafting adversarial examples for a single target class. This design results in clear limitations, such as low efficiency, restricted flexibility, and poor scalability in multi-target tasks, making them difficult to apply in complex scenarios where multiple targets must be addressed simultaneously. To address these challenges, we propose a multi-target generative attack based on dual-information (MTGA-DI). MTGA-DI employs a conditional generative model that integrates both semantic and visual information from multiple target classes, enabling efficient and adaptable multi-target attacks. Furthermore, the method significantly improves the transferability and stability of generated adversarial examples across different models and defense settings. Experimental results demonstrate that MTGA-DI surpasses previous methods on standard models as well as models enhanced with robust training and input preprocessing defenses, achieving higher attack success rates and better generalization.

  • Yiming Li, Yaxin Yu, Zhisheng Yu, Yiting Si, Yusong Ye
    Journal of Computer Research and Development. 2026, 63(1): 147-161. doi:10.7544/issn1000-1239.202550040

    Multimodal recommendation systems aim to deliver more accurate and personalized recommendations by leveraging diverse data modalities such as text and images. Despite their potential, existing approaches face several critical challenges. 1) Feature distortion. The input embeddings are processed by relatively small pre-trained language models and deep convolutional neural networks, which may lead to inaccurate and incomplete feature representations. 2) Single encoding perspective. The multimodal encoding layers of current models only consider encoding from a single perspective that is either memory-based or expansion-based, which limits representational capacity and leads to information loss. 3) Poor multimodal alignment. Embeddings from different modalities are distributed in distinct and heterogeneous semantic spaces, and need to be effectively mapped into a shared semantic space to achieve accurate alignment. However, existing methods typically rely on simple operations such as direct product of behavioral information, which cannot adequately capture the complex and high-order relationships among modalities. As a result, precise alignment across multiple modalities is difficult to achieve. To address these issues, we propose a novel model named DPRec. This model considers encoding from both memory and expansion perspectives and introduces hypergraphs for multi-level precise cross-modal alignment. The model is evaluated through extensive experiments on three real-world datasets. Experimental results confirm the effectiveness of DPRec, demonstrating its superiority over state-of-the-art approaches in improving recommendation accuracy.

  • Chenyang Li, Chaohong Ma, Xiaofeng Meng
    Journal of Computer Research and Development. 2026, 63(1): 41-65. doi:10.7544/issn1000-1239.202550195

    The booming of artificial intelligence (AI) plays a crucial role in various fields (e.g., healthcare, bioinformatics, and financial services). The main paradigm of AI applications involves building machine learning models to explore insights and patterns within data, which are then utilized for reasoning and decision-making. The effectiveness and efficiency of AI systems hinge on two key factors: the first is the model aspect (model-centric), involving the enhancement of network structure like the transitioning from RNN to LSTM, and the optimization of model hyperparameters; the second is the data aspect (data-centric), such as standardizing data formats, increasing data size, reducing data noises. For a long time, debugging AI systems primarily focuses on optimizing models. However, the rise of the digital era, characterized by activities such as social networking and e-commerce, has produced vast and varied data sets, making model-centric debugging fall short of fulfilling the requirements of modern applications. Consequently, both research and industry communities have redirected their focus from models to data to address this gap. To this end, “data debugging” has emerged. Rather than tuning model, data debugging places emphasis on scrutinizing data, which understands the impact of data errors on downstream tasks at each stage of machine learning pipeline, and then debug the corresponding errors to improve model performance. On the basis of a comprehensive survey of data debugging related work, the research framework for data debugging is first proposed. According to the interaction between data debugging methods and machine learning pipeline, the existing methods are categorized into closed data debugging, immersive data debugging, and hybrid data debugging. Then, we thoroughly provide a detailed overview of related work in this field. Next, we empirically evaluate data debugging methods, and summarize the commonly used datasets and evaluation metrics in this research area. Finally, the challenges and future directions of data debugging are pointed out.

  • Zhongsheng Qian, Hui Zhu, Qingyuan Yu, Yulong Li, Zilong Wan
    Journal of Computer Research and Development. 2026, 63(2): 352-377. doi:10.7544/issn1000-1239.202440737

    Social recommender systems explore collaborative data behind social labels to offer personalized suggestions. Despite many users lacking explicit social connections, they share similar item interaction histories. Prior studies have tried extracting high-order implicit social features via complex metapaths, which often diminishes model practicality. Additionally, the noise in these features can reduce adaptability when combined with explicit features using concatenation or deep learning. Recently, generative adversarial networks (GANs) have supported robust data augmentation but pose challenges with model convergence, impacting efficiency in social recommendation contexts. To address these issues, we introduce AFS-GAN (generative adversarial networks recommender systems for adaptive fusion of social features), a generative adversarial recommendation model with an adaptive fusion strategy for user social features. Initially, two simple metapaths extract first-order explicit and second-order implicit social features, improving model practicality and reducing subjective bias. An adaptive factor then flexibly fuses these features, capturing the diversity of user behaviors and enhancing recommendation adaptability. The generator uses straight-through Gumbel Softmax to speed up pseudo-item generation, while the discriminator employs a quartic BPR (bayesian personalized ranking) loss function to optimize discrimination loss, thus speeding convergence and simplifying the model. Extensive comparisons on 4 benchmark recommendation datasets with 8 leading social recommendation models have demonstrated that our approach excels in Precision, Recall, and NDCG metrics.

  • Haojun Ai, Feng Zhang, Pengfei Lü, Xuehua Tang, Zhongyuan Wang
    Journal of Computer Research and Development. 2026, 63(2): 338-351. doi:10.7544/issn1000-1239.202440951

    In recent years, self-supervised monocular depth estimation methods have achieved impressive improvements. However, their performance degrades significantly when generating structured depth maps in complex indoor scenarios. To bridge this gap, focusing on the training process, we propose LoFtDepth, a novel method that combines self-supervised monocular depth estimation with local feature guided knowledge distillation. Firstly, an off-the-shelf depth estimation network is used to generate structured relative depth maps as depth priors. Local features are then extracted from these priors as boundary points, guiding the local depth refinement. This reduces the interference of depth-irrelevant features and transfers the boundary knowledge of depth priors to the self-supervised depth estimation network. Additionally, we introduce an inverse auto-mask weighted surface normal loss. This encourages normal directions of depth maps predicted by self-supervised network to align with those of depth priors in untextured regions. As a result, the depth estimation accuracy is enhanced. Finally, according to the coherence of camera motion, we impose a pose consistency constraint on residual pose estimation. This constraint enables effective adaptation to indoor scenes where camera poses change frequently, thereby mitigating training errors and boosting model performance. Extensive experiments on major indoor datasets demonstrate that LoFtDepth outperforms previous methods. It reduces the absolute relative error to 0.121, and successfully generates accurate and well-structured depth maps.

  • Feixiang Zhang, Zhihua Li, Jianjun Liu
    Journal of Computer Research and Development. 2026, 63(2): 460-476. doi:10.7544/issn1000-1239.202550014

    In the field image reconstruction, traditional total variation (TV) regularization often incurs staircase artifacts and compromises image contrast. In this work, we refine the total variation framework by incorporating a non-convex penalty function alongside a backward diffusion mechanism; on this basis, we propose a resilient total variation (RTV)-based image reconstruction model. First, to mitigate staircase artifacts, the proposed method enhances the robustness of TV regularization by incorporating the transformed ${l_1}$ non-convex penalty functions, which improve the model’s adherence to the restricted isometry property (RIP). Second, to mitigate contrast loss in the reconstructed image and suppress noise, a backward diffusion mechanism is incorporated into the model to ensure smoothness in homogeneous regions. Subsequently, based on the RIP conditions, we derive theoretical guarantees for the stable reconstruction of the RTV image reconstruction model. The developed model is solved using a combination scheme of DC (difference of convex functions) programming and the alternating direction multiplier method, yielding an efficient resilient total variation-based reconstruction method. Extensive experiments on standard, natural, and medical images validate the method’s efficacy. The results demonstrate that the proposed method achieves superior reconstruction quality in comparison to the state-of-the-art methods, particularly in under-sampled and noisy scenarios, highlighting its effectiveness, efficiency, and practical utility.

  • Jinjiang Wang, Xiao Zhang, Linxuan Su, Jinyang Yu, Zhijie Huang, Yiwei Gan, Helang He, Ngulube Michael
    Journal of Computer Research and Development. 2026, 63(3): 668-684. doi:10.7544/issn1000-1239.202550482

    Modern blockchain systems face increasing storage pressure due to the continuous growth of on-chain data volume. Most systems adopt LSM-tree-based key-value storage engines as their persistence layer, which maintains intra-level key order through compaction. However, blockchain data are highly heterogeneous, characterized by structurally diverse and unordered keys. This results in frequent compaction operations that cause write amplification and degrade I/O efficiency. To address these issues, we propose AppendChain, a storage optimization framework that reorganizes the write path and key-value layout in the storage engine without altering Ethereum’s execution semantics. AppendChain introduces three techniques: 1) Type Separation: partitioning heterogeneous key types into dedicated column families to minimize keyspace overlap; 2) Big Value Separation: redirecting large values to external blob storage to avoid redundant rewrites during compaction; 3) Sorted Merkle Patricia Trie (MPT): applying structure-aware and order-aligned key encoding to enhance the locality of state keys. We implement AppendChain on top of Go-Ethereum (Geth) and integrate it with RocksDB, modifying the storage stack without changing Ethereum’s consensus and provenance logic. Evaluations on mainnet workloads show that, compared with Geth, AppendChain improves storage engine throughput (OPS) by up to 28 times, reduces write amplification rate nearly 94.24%, and reduces compaction frequency and time 98.75% and 72.19% respectively, significantly enhancing read/write efficiency under high-throughput transactional workloads. This framework effectively improves the storage performance of blockchain full nodes.

  • Zituo Li, Jianbin Sun, Guangzhou Chen, Xinyue Fang, Ruijing Cui, Zhiliang Tian, Zhen Huang, Kewei Yang
    Journal of Computer Research and Development. 2026, 63(1): 123-146. doi:10.7544/issn1000-1239.202550069

    In recent years, large language models (LLMs) have made significant strides in the field of natural language processing (NLP), demonstrating impressive capabilities in both language understanding and generation. However, despite these advancements, LLMs still face numerous challenges in practical applications. One such issue that has garnered extensive attention from both the academic and industrial communities is the problem of hallucinations. Effectively detecting hallucinations in large language models is a critical challenge for ensuring their reliable, secure, and trustworthy application in downstream tasks such as text generation. We provide a comprehensive review of methods for detecting hallucinations in large language models. Firstly, we introduce the concept of large language models and clarify the definition and classification of hallucinations. Then we systematically examine the characteristics of LLMs throughout their entire lifecycle, from construction to deployment, and delve into the mechanisms and causes of hallucinations. Secondly, based on practical application requirements and considering factors such as model transparency in different task scenarios, we categorize hallucination detection methods into two types: those for white-box models and those for black-box models. A focused review and in-depth comparison of these methods are provided. Then we analyze and summarize the current mainstream benchmarks for hallucination detection, laying a foundation for future research in this area. Finally, we identify various potential research directions and new challenges in the detection of hallucinations in large language models.