arXiv subjects

Zihan Chen

Publications and source records attributed to Zihan Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Navigating Sparsities in High-Dimensional Linear Contextual Bandits

High-dimensional linear contextual bandit problems remain a significant challenge due to the curse of dimensionality. Existing methods typically consider either the model parameters to be sparse or the eigenvalues of context covariance matrices to be (approximately) sparse, lacking general applicability due to the rigidity of conventional reward estimators. To overcome this limitation, a powerful pointwise estimator is introduced in this work that adaptively navigates both kinds of sparsity. Based on this pointwise estimator, a novel algorithm, termed HOPE, is proposed. Theoretical analyses demonstrate that HOPE not only achieves improved regret bounds in previously discussed homogeneous settings (i.e., considering only one type of sparsity) but also, for the first time, efficiently handles two new challenging heterogeneous settings (i.e., considering a mixture of two types of sparsity), highlighting its flexibility and generality. Experiments corroborate the superiority of HOPE over existing methods across various scenarios.

math.ST↗

arXiv2025

Voyager: An End-to-End Framework for Design-Space Exploration and Generation of DNN Accelerators

While deep neural networks (DNNs) have achieved state-of-the-art performance in fields from computer vision to natural language processing, efficiently running these computationally demanding models requires hardware accelerators. However, designing these accelerators is a time-consuming, labor-intensive process that does not scale well. While prior efforts have sought to automate DNN accelerator generation, they offer limited parameterization, cannot produce high-performance, tapeout-ready designs, provide limited support for datatypes and quantization schemes, and lack an integrated, end-to-end software compiler. This work proposes Voyager, a high-level synthesis (HLS)-based framework for design space exploration (DSE) and generation of DNN accelerators. Voyager overcomes the limitations of prior work by offering extensive configurability across technology nodes, clock frequencies, and scales, with customizable parameters such as number of processing elements, on-chip buffer sizes, and external memory bandwidth. Voyager supports a wider variety of datatypes and quantization schemes versus prior work, including both built-in floating-point, posit and integer formats, as well as user-defined formats with both per-tensor scaling and microscaling quantization. Voyager's PyTorch-based compiler efficiently maps networks end-to-end on the generated hardware, with support for quantization, fusion, and tiling. We evaluate Voyager on state-of-the-art vision and language models. Voyager enables fast DSE with full-dataset accuracy evaluation for datatypes and quantization schemes. Generated designs achieve a high utilization across models and scales, up to 99.8%, and outperform prior generators with up to 61% lower latency and 56% lower area. Compared to hand-optimized accelerators, Voyager achieves comparable performance, while offering much greater automation in design and workload mapping.

cs.AR↗

arXiv2025

ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval

Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a best performance-cost trade-off, we propose ALLabel, a three-stage framework designed to select the most informative and representative samples in preparing the demonstrations for LLM modeling. The annotated examples are used to construct a ground-truth retrieval corpus for LLM in-context learning. By sequentially employing three distinct active learning strategies, ALLabel consistently outperforms all baselines under the same annotation budget across three specialized domain datasets. Experimental results also demonstrate that selectively annotating only 5\%-10\% of the dataset with ALLabel can achieve performance comparable to the method annotating the entire dataset. Further analyses and ablation studies verify the effectiveness and generalizability of our proposal.

cs.CL↗

arXiv2025

Learning from Diverse Reasoning Paths with Routing and Collaboration

Advances in large language models (LLMs) significantly enhance reasoning capabilities but their deployment is restricted in resource-constrained scenarios. Knowledge distillation addresses this by transferring knowledge from powerful teacher models to compact and transparent students. However, effectively capturing the teacher's comprehensive reasoning is challenging due to conventional token-level supervision's limited scope. Using multiple reasoning paths per query alleviates this problem, but treating each path identically is suboptimal as paths vary widely in quality and suitability across tasks and models. We propose Quality-filtered Routing with Cooperative Distillation (QR-Distill), combining path quality filtering, conditional routing, and cooperative peer teaching. First, quality filtering retains only correct reasoning paths scored by an LLM-based evaluation. Second, conditional routing dynamically assigns paths tailored to each student's current learning state. Finally, cooperative peer teaching enables students to mutually distill diverse insights, addressing knowledge gaps and biases toward specific reasoning styles. Experiments demonstrate QR-Distill's superiority over traditional single- and multi-path distillation methods. Ablation studies further highlight the importance of each component including quality filtering, conditional routing, and peer teaching in effective knowledge transfer. Our code is available at https://github.com/LzyFischer/Distill.

cs.CL↗

arXiv2025

PRIME: Plasticity-Robust Incremental Model for Encrypted Traffic Classification in Dynamic Network Environments

With the continuous development of network environments and technologies, ensuring cyber security and governance is increasingly challenging. Network traffic classification(ETC) can analyzes attributes such as application categories and malicious intent, supporting network management services like QoS optimization, intrusion detection, and targeted billing. As the prevalence of traffic encryption increases, deep learning models are relied upon for content-agnostic analysis of packet sequences. However, the emergence of new services and attack variants often leads to incremental tasks for ETC models. To ensure model effectiveness, incremental learning techniques are essential; however, recent studies indicate that neural networks experience declining plasticity as tasks increase. We identified plasticity issues in existing incremental learning methods across diverse traffic samples and proposed the PRIME framework. By observing the effective rank of model parameters and the proportion of inactive neurons, the PRIME architecture can appropriately increase the parameter scale when the model's plasticity deteriorates. Experiments show that in multiple encrypted traffic datasets and different category increment scenarios, the PRIME architecture performs significantly better than other incremental learning algorithms with minimal increase in parameter scale.

cs.NI↗

arXiv2025

Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection

The natural combination of intricate topological structures and rich textual information in text-attributed graphs (TAGs) opens up a novel perspective for graph anomaly detection (GAD). However, existing GAD methods primarily focus on designing complex optimization objectives within the graph domain, overlooking the complementary value of the textual modality, whose features are often encoded by shallow embedding techniques, such as bag-of-words or skip-gram, so that semantic context related to anomalies may be missed. To unleash the enormous potential of textual modality, large language models (LLMs) have emerged as promising alternatives due to their strong semantic understanding and reasoning capabilities. Nevertheless, their application to TAG anomaly detection remains nascent, and they struggle to encode high-order structural information inherent in graphs due to input length constraints. For high-quality anomaly detection in TAGs, we propose CoLL, a novel framework that combines LLMs and graph neural networks (GNNs) to leverage their complementary strengths. CoLL employs multi-LLM collaboration for evidence-augmented generation to capture anomaly-relevant contexts while delivering human-readable rationales for detected anomalies. Moreover, CoLL integrates a GNN equipped with a gating mechanism to adaptively fuse textual features with evidence while preserving high-order topological information. Extensive experiments demonstrate the superiority of CoLL, achieving an average improvement of 13.37% in AP. This study opens a new avenue for incorporating LLMs in advancing GAD.

cs.LG↗

arXiv2025

Robust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clipping

Leveraging over-the-air computations for model aggregation is an effective approach to cope with the communication bottleneck in federated edge learning. By exploiting the superposition properties of multi-access channels, this approach facilitates an integrated design of communication and computation, thereby enhancing system privacy while reducing implementation costs. However, the inherent electromagnetic interference in radio channels often exhibits heavy-tailed distributions, giving rise to exceptionally strong noise in globally aggregated gradients that can significantly deteriorate the training performance. To address this issue, we propose a novel gradient clipping method, termed Median Anchored Clipping (MAC), to combat the detrimental effects of heavy-tailed noise. We also derive analytical expressions for the convergence rate of model training with analog over-the-air federated learning under MAC, which quantitatively demonstrates the effect of MAC on training performance. Extensive experimental results show that the proposed MAC algorithm effectively mitigates the impact of heavy-tailed noise, hence substantially enhancing system robustness.

cs.LG↗

arXiv2025

Graph Prompting for Graph Learning Models: Recent Advances and Future Directions

Graph learning models have demonstrated great prowess in learning expressive representations from large-scale graph data in a wide variety of real-world scenarios. As a prevalent strategy for training powerful graph learning models, the "pre-training, adaptation" scheme first pre-trains graph learning models on unlabeled graph data in a self-supervised manner and then adapts them to specific downstream tasks. During the adaptation phase, graph prompting emerges as a promising approach that learns trainable prompts while keeping the pre-trained graph learning models unchanged. In this paper, we present a systematic review of recent advancements in graph prompting. First, we introduce representative graph pre-training methods that serve as the foundation step of graph prompting. Next, we review mainstream techniques in graph prompting and elaborate on how they design learnable prompts for graph prompting. Furthermore, we summarize the real-world applications of graph prompting from different domains. Finally, we discuss several open challenges in existing studies with promising future directions in this field.

cs.LG↗

arXiv2025

Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy

Unthinking execution of human instructions in robotic manipulation can lead to severe safety risks, such as poisonings, fires, and even explosions. In this paper, we present responsible robotic manipulation, which requires robots to consider potential hazards in the real-world environment while completing instructions and performing complex operations safely and efficiently. However, such scenarios in real world are variable and risky for training. To address this challenge, we propose Safety-as-policy, which includes (i) a world model to automatically generate scenarios containing safety risks and conduct virtual interactions, and (ii) a mental model to infer consequences with reflections and gradually develop the cognition of safety, allowing robots to accomplish tasks while avoiding dangers. Additionally, we create the SafeBox synthetic dataset, which includes one hundred responsible robotic manipulation tasks with different safety risk scenarios and instructions, effectively reducing the risks associated with real-world experiments. Experiments demonstrate that Safety-as-policy can avoid risks and efficiently complete tasks in both synthetic dataset and real-world experiments, significantly outperforming baseline methods. Our SafeBox dataset shows consistent evaluation results with real-world scenarios, serving as a safe and effective benchmark for future research.

cs.RO↗

arXiv2025

FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs

Federated Graph Learning (FGL) empowers clients to collaboratively train Graph neural networks (GNNs) in a distributed manner while preserving data privacy. However, FGL methods usually require that the graph data owned by all clients is homophilic to ensure similar neighbor distribution patterns of nodes. Such an assumption ensures that the learned knowledge is consistent across the local models from all clients. Therefore, these local models can be properly aggregated as a global model without undermining the overall performance. Nevertheless, when the neighbor distribution patterns of nodes vary across different clients (e.g., when clients hold graphs with different levels of heterophily), their local models may gain different and even conflict knowledge from their node-level predictive tasks. Consequently, aggregating these local models usually leads to catastrophic performance deterioration on the global model. To address this challenge, we propose FedHERO, an FGL framework designed to harness and share insights from heterophilic graphs effectively. At the heart of FedHERO is a dual-channel GNN equipped with a structure learner, engineered to discern the structural knowledge encoded in the local graphs. With this specialized component, FedHERO enables the local model for each client to identify and learn patterns that are universally applicable across graphs with different patterns of node neighbor distributions. FedHERO not only enhances the performance of individual client models by leveraging both local and shared structural insights but also sets a new precedent in this field to effectively handle graph data with various node neighbor distribution patterns. We conduct extensive experiments to validate the superior performance of FedHERO against existing alternatives.

cs.LG↗

arXiv2025

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle diverse tasks by incorporating multiple input-output examples, known as demonstrations, into the input of LLMs. More recently, advancements in the expanded context windows of LLMs have led to many-shot ICL, which uses hundreds of demonstrations and outperforms few-shot ICL, which relies on fewer examples. However, this approach is often hindered by the high cost of obtaining large amounts of labeled data. To address this challenge, we propose Many-Shot Adaptive Pseudo-LabEling, namely MAPLE, a novel influence-based many-shot ICL framework that utilizes pseudo-labeled samples to compensate for the lack of label information. We first identify a subset of impactful unlabeled samples and perform pseudo-labeling on them by querying LLMs. These pseudo-labeled samples are then adaptively selected and tailored to each test query as input to improve the performance of many-shot ICL, without significant labeling costs. Extensive experiments on real-world datasets demonstrate the effectiveness of our framework, showcasing its ability to enhance LLM adaptability and performance with limited labeled data.

cs.AI↗

arXiv2025

Genesis: A Compiler Framework for Hamiltonian Simulation on Hybrid CV-DV Quantum Computers

This paper introduces Genesis, the first compiler designed to support Hamiltonian Simulation on hybrid continuous-variable (CV) and discrete-variable (DV) quantum computing systems. Genesis is a two-level compilation system. At the first level, it decomposes an input Hamiltonian into basis gates using the native instruction set of the target hybrid CV-DV quantum computer. At the second level, it tackles the mapping and routing of qumodes/qubits to implement long-range interactions for the gates decomposed from the first level. Rather than a typical implementation that relies on SWAP primitives similar to qubit-based (or DV-only) systems, we propose an integrated design of connectivity-aware gate synthesis and beamsplitter SWAP insertion tailored for hybrid CV-DV systems. We also introduce an OpenQASM-like domain-specific language (DSL) named CVDV-QASM to represent Hamiltonian in terms of Pauli-exponentials and basic gate sequences from the hybrid CV-DV gate set. Genesis has successfully compiled several important Hamiltonians, including the Bose-Hubbard model, $\mathbb{Z}_2-$Higgs model, Hubbard-Holstein model, Heisenberg model and Electron-vibration coupling Hamiltonians, which are critical in domains like quantum field theory, condensed matter physics, and quantum chemistry. Our implementation is available at Genesis-CVDV-Compiler(https://github.com/ruadapt/Genesis-CVDV-Compiler).

quant-ph↗

arXiv2025

Towards Secure Semantic Transmission In the Era of GenAI: A Diffusion-based Framework

Semantic communication, due to its focus on the transmitting meaning rather than the raw bit data, poses unique security challenges compared to the traditional communication systems. In particular, semantic communication systems are vulnerable to the malicious attacks that focus on the semantic layer, with the intention of understanding or distorting the intended meaning of the transmitted privacy data. Diffusion models, a class of generative artificial intelligence (GenAI), are well-suited for ensuring data security to attack. Through iteratively adding and then removing noise, diffusion models can generate meaningful information despite the presence of the unknown noise. This article proposes a diffusion-based framework to enhance the security of semantic transmission for the attacks including eavesdropping and jamming. Specifically, the proposed framework incorporates both the artificial noise and natural channel noise into the forward process of the diffusion models during the semantic transmission, with the reverse process used to remove noise at the legitimate receiver. In the eavesdropping scenarios, the artificial noise is the friendly noise designed to prevent semantic eavesdropping. In the jamming scenarios, the artificial noise is the malicious jamming generated by the jammer, which disrupts the semantic transmission. The case studies show that the proposed diffusion-based framework is promising in securing the semantic transmission. We also consolidate several broad research directions associated with the proposed framework.

cs.IT↗

arXiv2025

Diffusion-enabled Secure Semantic Communication Against Eavesdropping

In this paper, AN is introduced into semantic communication systems for the first time to prevent semantic eavesdropping. However, the introduction of AN also poses challenges for the legitimate receiver in extracting semantic information. Recently, denoising diffusion probabilistic models (DDPM) have demonstrated their powerful capabilities in generating multimedia content. Here, the paired pluggable modules are carefully designed using DDPM. Specifically, the pluggable encryption module generates AN and adds it to the output of the semantic transmitter, while the pluggable decryption module before semantic receiver uses DDPM to generate the detailed semantic information by removing both AN and the channel noise. In the scenario where the transmitter lacks eavesdropper's knowledge, the artificial Gaussian noise (AGN) is used as AN. We first model a power allocation optimization problem to determine the power of AGN, in which the objective is to minimize the weighted sum of data reconstruction error of legal link, the mutual information of illegal link, and the channel input distortion. Then, a deep reinforcement learning framework using deep deterministic policy gradient is proposed to solve the optimization problem. In the scenario where the transmitter is aware of the eavesdropper's knowledge, we propose an AN generation method based on adversarial residual networks (ARN). Unlike the previous scenario, the mutual information term in the objective function is replaced by the confidence of eavesdropper correctly retrieving private information. The adversarial residual network is then trained to minimize the modified objective function. The simulation results show that the diffusion-enabled pluggable encryption module prevents semantic eavesdropping while the pluggable decryption module achieves the high-quality semantic communication.

cs.IT↗

arXiv2025

Rethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading

Recently, DeepSeek-R1 (671B) (DeepSeek-AIet al., 2025) has demonstrated its excellent reasoning ability in complex tasks and has publiclyshared its methodology. This provides potentially high-quality chain-of-thought (CoT) data for stimulating the reasoning abilities of small-sized large language models (LLMs). To generate high-quality CoT data for different LLMs, we seek an efficient method for generating high-quality CoT data with LLM-Adaptive questiondifficulty levels. First, we grade the difficulty of the questions according to the reasoning ability of the LLMs themselves and construct a LLM-Adaptive question database. Second, we sample the problem database based on a distribution of difficulty levels of the questions and then use DeepSeek-R1 (671B) (DeepSeek-AI et al., 2025) to generate the corresponding high-quality CoT data with correct answers. Thanks to the construction of CoT data with LLM-Adaptive difficulty levels, we have significantly reduced the cost of data generation and enhanced the efficiency of model supervised fine-tuning (SFT). Finally, we have validated the effectiveness and generalizability of the proposed method in the fields of complex mathematical competitions and code generation tasks. Notably, with only 2k high-quality mathematical CoT data, our ZMath-32B surpasses DeepSeek-Distill-32B in math reasoning task. Similarly, with only 2k high-quality code CoT data, our ZCode-32B surpasses DeepSeek-Distill-32B in code reasoning tasks.

cs.AI↗

arXiv2025

SNAKE: A Sustainable and Multi-functional Traffic Analysis System utilizing Specialized Large-Scale Models with a Mixture of Experts Architecture

The rapid advancement of internet technology has led to a surge in data transmission, making network traffic classification crucial for security and management. However, there are significant deficiencies in its efficiency for handling multiattribute analysis and its ability to expand model knowledge, making it difficult to adapt to the ever-changing network environment and complex identification requirements. To address this issue, we proposed the SNAKE (Sustainable Network Analysis with Knowledge Exploration) system, which adopts a multi-gated mixture of experts architecture to construct a multi-functional traffic classification model. The system analyzes traffic attributes at different levels through multiple expert sub-models, providing predictions for these attributes via gating and a final Tower network. Additionally, through an intelligent gating configuration, the system enables extremely fast model integration and evolution across various knowledge expansion scenarios. Its excellent compatibility allows it to continuously evolve into a multi-functional largescale model in the field of traffic analysis. Our experimental results demonstrate that the SNAKE system exhibits remarkable scalability when faced with incremental challenges in diverse traffic classification tasks. Currently, we have integrated multiple models into the system, enabling it to classify a wide range of attributes, such as encapsulation usage, application types and numerous malicious behaviors. We believe that SNAKE can pioneeringly create a sustainable and multifunctional large-scale model in the field of network traffic analysis after continuous expansion.

cs.NI↗

arXiv2025

SMILENet: Unleashing Extra-Large Capacity Image Steganography via a Synergistic Mosaic InvertibLE Hiding Network

Existing image steganography methods face fundamental limitations in hiding capacity (typically $1\sim7$ images) due to severe information interference and uncoordinated capacity-distortion trade-off. We propose SMILENet, a novel synergistic framework that achieves 25 image hiding through three key innovations: (i) A synergistic network architecture coordinates reversible and non-reversible operations to efficiently exploit information redundancy in both secret and cover images. The reversible Invertible Cover-Driven Mosaic (ICDM) module and Invertible Mosaic Secret Embedding (IMSE) module establish cover-guided mosaic transformations and representation embedding with mathematically guaranteed invertibility for distortion-free embedding. The non-reversible Secret Information Selection (SIS) module and Secret Detail Enhancement (SDE) module implement learnable feature modulation for critical information selection and enhancement. (ii) A unified training strategy that coordinates complementary modules to achieve 3.0x higher capacity than existing methods with superior visual quality. (iii) Last but not least, we introduce a new metric to model Capacity-Distortion Trade-off for evaluating the image steganography algorithms that jointly considers hiding capacity and distortion, and provides a unified evaluation approach for accessing results with different number of secret image. Extensive experiments on DIV2K, Paris StreetView and ImageNet1K show that SMILENet outperforms state-of-the-art methods in terms of hiding capacity, recovery quality as well as security against steganalysis methods.

cs.CV↗

arXiv2025

A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal

Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8\% of the parameters required by leading methods.

eess.IV↗