arXiv subjects

Haibing Guan

Publications and source records attributed to Haibing Guan.

At least 55 records · Page 3Linked to original sources

arXiv2025

PUSHtap: PIM-based In-Memory HTAP with Unified Data Storage Format

Hybrid transaction/analytical processing (HTAP) is an emerging database paradigm that supports both online transaction processing (OLTP) and online analytical processing (OLAP) workloads. Computing-intensive OLTP operations, involving row-wise data manipulation, are suitable for row-store format. In contrast, memory-intensive OLAP operations, which are column-centric, benefit from column-store format. This \emph{data-format dilemma} prevents HTAP systems from concurrently achieving three design goals: performance isolation, data freshness, and workload-specific optimization. Another background technology is Processing-in-Memory (PIM), which integrates computing units (PIM units) inside DRAM memory devices to accelerate memory-intensive workloads, including OLAP. Our key insight is to combine the interleaved CPU access and localized PIM unit access to provide two-dimensional access to address the data format contradictions inherent in HTAP. First, we propose a unified data storage format with novel data alignment and placement techniques to optimize the effective bandwidth of CPUs and PIM units and exploit the PIM's parallelism. Second, we implement the multi-version concurrency control (MVCC) essential for single-instance HTAP. Third, we extend the commercial PIM architecture to support the OLAP operations and concurrent access from PIM and CPU. Experiments show that PUSHtap can achieve 3.4\texttimes{}/4.4\texttimes{} OLAP/OLTP throughput improvement compared to multi-instance PIM-based design.

cs.DC↗

arXiv2025

Dissecting the Impact of Mobile DVFS Governors on LLM Inference Performance and Energy Efficiency

Large Language Models (LLMs) are increasingly being integrated into various applications and services running on billions of mobile devices. However, deploying LLMs on resource-limited mobile devices faces a significant challenge due to their high demand for computation, memory, and ultimately energy. While current LLM frameworks for mobile use three power-hungry components-CPU, GPU, and Memory-even when running primarily-GPU LLM models, optimized DVFS governors for CPU, GPU, and memory featured in modern mobile devices operate independently and are oblivious of each other. Motivated by the above observation, in this work, we first measure the energy-efficiency of a SOTA LLM framework consisting of various LLM models on mobile phones which showed the triplet mobile governors result in up to 40.4% longer prefilling and decoding latency compared to optimal combinations of CPU, GPU, and memory frequencies with the same energy consumption for sampled prefill and decode lengths. Second, we conduct an in-depth measurement study to uncover how the intricate interplay (or lack of) among the mobile governors cause the above inefficiency in LLM inference. Finally, based on these insights, we design FUSE - a unified energy-aware governor for optimizing the energy efficiency of LLM inference on mobile devices. Our evaluation using a ShareGPT dataset shows FUSE reduces the time-to-first-token and time-per-output-token latencies by 7.0%-16.9% and 25.4%-36.8% on average with the same energy-per-token for various mobile LLM models.

cs.OS↗

arXiv2025

ALLMod: Exploring $\underline{\mathbf{A}}$rea-Efficiency of $\underline{\mathbf{L}}$UT-based $\underline{\mathbf{L}}$arge Number $\underline{\mathbf{Mod}}$ular Reduction via Hybrid Workloads

Modular arithmetic, particularly modular reduction, is widely used in cryptographic applications such as homomorphic encryption (HE) and zero-knowledge proofs (ZKP). High-bit-width operations are crucial for enhancing security; however, they are computationally intensive due to the large number of modular operations required. The lookup-table-based (LUT-based) approach, a ``space-for-time'' technique, reduces computational load by segmenting the input number into smaller bit groups, pre-computing modular reduction results for each segment, and storing these results in LUTs. While effective, this method incurs significant hardware overhead due to extensive LUT usage. In this paper, we introduce ALLMod, a novel approach that improves the area efficiency of LUT-based large-number modular reduction by employing hybrid workloads. Inspired by the iterative method, ALLMod splits the bit groups into two distinct workloads, achieving lower area costs without compromising throughput. We first develop a template to facilitate workload splitting and ensure balanced distribution. Then, we conduct design space exploration to evaluate the optimal timing for fusing workload results, enabling us to identify the most efficient design under specific constraints. Extensive evaluations show that ALLMod achieves up to $1.65\times$ and $3\times$ improvements in area efficiency over conventional LUT-based methods for bit-widths of $128$ and $8,192$, respectively.

cs.CR↗

arXiv2025

DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies

Large language models (LLMs) have achieved remarkable performance across a wide range of NLP tasks. However, their substantial inference cost poses a major barrier to real-world deployment, especially in latency-sensitive scenarios. To address this challenge, we propose \textbf{DASH}, an adaptive layer-skipping framework that dynamically selects computation paths conditioned on input characteristics. We model the skipping process as a Markov Decision Process (MDP), enabling fine-grained token-level decisions based on intermediate representations. To mitigate potential performance degradation caused by skipping, we introduce a lightweight compensation mechanism that injects differential rewards into the decision process. Furthermore, we design an asynchronous execution strategy that overlaps layer computation with policy evaluation to minimize runtime overhead. Experiments on multiple LLM architectures and NLP benchmarks show that our method achieves significant inference acceleration while maintaining competitive task performance, outperforming existing methods.

cs.CL↗

arXiv2025

LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillation

Large language models (LLMs) have achieved significant progress in natural language processing but face challenges in deployment due to high memory and computational requirements. Weight quantization is a common approach to address these issues, yet achieving effective low-bit compression remains challenging. This paper presents LCD, which unifies the learning of clustering-based quantization within a knowledge distillation framework. Using carefully designed optimization techniques, LCD preserves LLM performance even at ultra-low bit widths of 2-3 bits. Additionally, LCD compresses activations through smoothing and accelerates inference with a LUT-based design. Experimental results show that LCD outperforms existing methods and delivers up to a 6.2x speedup in inference. Notably, LCD is shown to be more cost-effective, making it a practical solution for real-world applications.

cs.LG↗

arXiv2025

STRCMP: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization

Combinatorial optimization (CO) problems, central to operation research and theoretical computer science, present significant computational challenges due to their NP-hard nature. While large language models (LLMs) have emerged as promising tools for CO--either by directly generating solutions or synthesizing solver-specific codes--existing approaches often neglect critical structural priors inherent to CO problems, leading to suboptimality and iterative inefficiency. Inspired by human experts' success in leveraging CO structures for algorithm design, we propose STRCMP, a novel structure-aware LLM-based algorithm discovery framework that systematically integrates structure priors to enhance solution quality and solving efficiency. Our framework combines a graph neural network (GNN) for extracting structural embeddings from CO instances with an LLM conditioned on these embeddings to identify high-performing algorithms in the form of solver-specific codes. This composite architecture ensures syntactic correctness, preserves problem topology, and aligns with natural language objectives, while an evolutionary refinement process iteratively optimizes generated algorithm. Extensive evaluations across Mixed Integer Linear Programming and Boolean Satisfiability problems, using nine benchmark datasets, demonstrate that our proposed STRCMP outperforms five strong neural and LLM-based methods by a large margin, in terms of both solution optimality and computational efficiency. The code and learned model will be publicly available upon the acceptance of the paper.

cs.LG↗

arXiv2025

MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization

Large language models (LLMs) are increasingly utilized for complex tasks requiring longer context lengths, with some models supporting up to 128K or 1M tokens. This trend, however, presents significant challenges in inference speed and memory management. Quantization emerges as a promising approach to address the widening gap between LLM size and memory capacity. However, traditional quantization schemes often yield suboptimal compression results for KV caches due to two key factors: i) On-the-fly quantization and de-quantization, causing significant performance overhead; ii) Prevalence of outliers in KV values, challenging low-bitwidth uniform quantization. To this end, we propose MILLION, a novel quantization framework achieving low-bitwidth KV cache through product quantization. First, we conduct a thorough analysis of KV cache distribution, revealing the limitations of existing quantization schemes. Second, we introduce a non-uniform quantization algorithm based on product quantization, which efficiently compresses data while preserving accuracy. Third, we develop a high-performance GPU inference framework with efficient attention kernel and pipeline design for MILLION that leverages sparse computation and asynchronous quantization, significantly enhancing inference speed. Comprehensive evaluation results demonstrate that MILLION can achieve 4 bits quantization with trivial perplexity and accuracy loss, and achieve 2.09x end-to-end performance gains at 32K context length. Code is released at https://github.com/ZongwuWang/MILLION.

cs.DC↗

arXiv2025

Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor Cores

The escalating size of Mixture-of-Experts (MoE) based Large Language Models (LLMs) presents significant computational and memory challenges, necessitating innovative solutions to enhance efficiency without compromising model accuracy. Structured sparsity emerges as a compelling strategy to address these challenges by leveraging the emerging sparse computing hardware. Prior works mainly focus on the sparsity in model parameters, neglecting the inherent sparse patterns in activations. This oversight can lead to additional computational costs associated with activations, potentially resulting in suboptimal performance. This paper presents Samoyeds, an innovative acceleration system for MoE LLMs utilizing Sparse Tensor Cores (SpTCs). Samoyeds is the first to apply sparsity simultaneously to both activations and model parameters. It introduces a bespoke sparse data format tailored for MoE computation and develops a specialized sparse-sparse matrix multiplication kernel. Furthermore, Samoyeds incorporates systematic optimizations specifically designed for the execution of dual-side structured sparse MoE LLMs on SpTCs, further enhancing system performance. Evaluations show that Samoyeds outperforms SOTA works by up to 1.99$\times$ at the kernel level and 1.58$\times$ at the model level. Moreover, it enhances memory efficiency, increasing maximum supported batch sizes by 4.41$\times$ on average. Additionally, Samoyeds surpasses existing SOTA structured sparse solutions in both model accuracy and hardware portability.

cs.LG↗

arXiv2025

Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning

Causal discovery is a structured prediction task that aims to predict causal relations among variables based on their data samples. Supervised Causal Learning (SCL) is an emerging paradigm in this field. Existing Deep Neural Network (DNN)-based methods commonly adopt the "Node-Edge approach", in which the model first computes an embedding vector for each variable-node, then uses these variable-wise representations to concurrently and independently predict for each directed causal-edge. In this paper, we first show that this architecture has some systematic bias that cannot be mitigated regardless of model size and data size. We then propose SiCL, a DNN-based SCL method that predicts a skeleton matrix together with a v-tensor (a third-order tensor representing the v-structures). According to the Markov Equivalence Class (MEC) theory, both the skeleton and the v-structures are identifiable causal structures under the canonical MEC setting, so predictions about skeleton and v-structures do not suffer from the identifiability limit in causal discovery, thus SiCL can avoid the systematic bias in Node-Edge architecture, and enable consistent estimators for causal discovery. Moreover, SiCL is also equipped with a specially designed pairwise encoder module with a unidirectional attention layer to model both internal and external relationships of pairs of nodes. Experimental results on both synthetic and real-world benchmarks show that SiCL significantly outperforms other DNN-based SCL approaches.

cs.LG↗

arXiv2025

THOR: A Generic Energy Estimation Approach for On-Device Training

Battery-powered mobile devices (e.g., smartphones, AR/VR glasses, and various IoT devices) are increasingly being used for AI training due to their growing computational power and easy access to valuable, diverse, and real-time data. On-device training is highly energy-intensive, making accurate energy consumption estimation crucial for effective job scheduling and sustainable AI. However, the heterogeneity of devices and the complexity of models challenge the accuracy and generalizability of existing estimation methods. This paper proposes THOR, a generic approach for energy consumption estimation in deep neural network (DNN) training. First, we examine the layer-wise energy additivity property of DNNs and strategically partition the entire model into layers for fine-grained energy consumption profiling. Then, we fit Gaussian Process (GP) models to learn from layer-wise energy consumption measurements and estimate a DNN's overall energy consumption based on its layer-wise energy additivity property. We conduct extensive experiments with various types of models across different real-world platforms. The results demonstrate that THOR has effectively reduced the Mean Absolute Percentage Error (MAPE) by up to 30%. Moreover, THOR is applied in guiding energy-aware pruning, successfully reducing energy consumption by 50%, thereby further demonstrating its generality and potential.

cs.LG↗

arXiv2024

Eliminating Domain Bias for Federated Learning in Representation Space

Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator (DBE) for FL. Our theoretical analysis reveals that DBE can promote bi-directional knowledge transfer between server and client, as it reduces the domain discrepancy between server and client in representation space. Besides, extensive experiments on four datasets show that DBE can greatly improve existing FL methods in both generalization and personalization abilities. The DBE-equipped FL method can outperform ten state-of-the-art personalized FL methods by a large margin. Our code is public at https://github.com/TsingZ0/DBE.

cs.LG↗

arXiv2024

SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks

Federated Learning (FL) is becoming a popular paradigm for leveraging distributed data and preserving data privacy. However, due to the distributed characteristic, FL systems are vulnerable to Byzantine attacks that compromised clients attack the global model by uploading malicious model updates. With the development of layer-level and parameter-level fine-grained attacks, the attacks' stealthiness and effectiveness have been significantly improved. The existing defense mechanisms solely analyze the model-level statistics of individual model updates uploaded by clients to mitigate Byzantine attacks, which are ineffective against fine-grained attacks due to unawareness or overreaction. To address this problem, we propose SkyMask, a new attack-agnostic robust FL system that firstly leverages fine-grained learnable masks to identify malicious model updates at the parameter level. Specifically, the FL server freezes and multiplies the model updates uploaded by clients with the parameter-level masks, and trains the masks over a small clean dataset (i.e., root dataset) to learn the subtle difference between benign and malicious model updates in a high-dimension space. Our extensive experiments involve different models on three public datasets under state-of-the-art (SOTA) attacks, where the results show that SkyMask achieves up to 14% higher testing accuracy compared with SOTA defense strategies under the same attacks and successfully defends against attacks with malicious clients of a high fraction up to 80%. Code is available at https://github.com/KoalaYan/SkyMask.

cs.CR↗

arXiv2024

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

Diffusion Models (DMs) have evolved into advanced image generation tools, especially for few-shot generation where a pretrained model is fine-tuned on a small set of images to capture a specific style or object. Despite their success, concerns exist about potential copyright violations stemming from the use of unauthorized data in this process. In response, we present Contrasting Gradient Inversion for Diffusion Models (CGI-DM), a novel method featuring vivid visual representations for digital copyright authentication. Our approach involves removing partial information of an image and recovering missing details by exploiting conceptual differences between the pretrained and fine-tuned models. We formulate the differences as KL divergence between latent variables of the two models when given the same input image, which can be maximized through Monte Carlo sampling and Projected Gradient Descent (PGD). The similarity between original and recovered images serves as a strong indicator of potential infringements. Extensive experiments on the WikiArt and Dreambooth datasets demonstrate the high accuracy of CGI-DM in digital copyright authentication, surpassing alternative validation techniques. Code implementation is available at https://github.com/Nicholas0228/Revelio.

cs.CV↗

arXiv2023

FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy

Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones, etc. Most existing pFL methods focus on exploiting the global information and personalized information in the client-level model parameters while neglecting that data is the source of these two kinds of information. To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively. FedCP is more fine-grained to consider personalization in a sample-specific manner than existing pFL methods. Extensive experiments in computer vision and natural language processing domains show that FedCP outperforms eleven state-of-the-art methods by up to 6.69%. Furthermore, FedCP maintains its superiority when some clients accidentally drop out, which frequently happens in mobile settings. Our code is public at https://github.com/TsingZ0/FedCP.

cs.LG↗

arXiv2023

GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning

Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization in FL. However, from the perspective of feature extraction, most existing pFL methods only focus on extracting global or personalized feature information during local training, which fails to meet the collaborative learning and personalization goals of pFL. To address this, we propose a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client. We conduct extensive experiments on six datasets in three statistically heterogeneous settings and show the superiority of GPFL over ten state-of-the-art methods regarding effectiveness, scalability, fairness, stability, and privacy. Besides, GPFL mitigates overfitting and outperforms the baselines by up to 8.99% in accuracy.

cs.LG↗

arXiv2023

FedALA: Adaptive Local Aggregation for Personalized Federated Learning

A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by capturing the desired information in the global model for client models in personalized FL. The key component of FedALA is an Adaptive Local Aggregation (ALA) module, which can adaptively aggregate the downloaded global model and local model towards the local objective on each client to initialize the local model before training in each iteration. To evaluate the effectiveness of FedALA, we conduct extensive experiments with five benchmark datasets in computer vision and natural language processing domains. FedALA outperforms eleven state-of-the-art baselines by up to 3.27% in test accuracy. Furthermore, we also apply ALA module to other federated learning methods and achieve up to 24.19% improvement in test accuracy.

cs.LG↗

arXiv2023

Chrion: Optimizing Recurrent Neural Network Inference by Collaboratively Utilizing CPUs and GPUs

Deploying deep learning models in cloud clusters provides efficient and prompt inference services to accommodate the widespread application of deep learning. These clusters are usually equipped with host CPUs and accelerators with distinct responsibilities to handle serving requests, i.e. generalpurpose CPUs for input preprocessing and domain-specific GPUs for forward computation. Recurrent neural networks play an essential role in handling temporal inputs and display distinctive computation characteristics because of their high inter-operator parallelism. Hence, we propose Chrion to optimize recurrent neural network inference by collaboratively utilizing CPUs and GPUs. We formulate the model deployment in the CPU-GPU cluster as an NP-hard scheduling problem of directed acyclic graphs on heterogeneous devices. Given an input model in the ONNX format and user-defined SLO requirement, Chrion firstly preprocesses the model by model parsing and profiling, and then partitions the graph to select execution devices for each operator. When an online request arrives, Chrion performs forward computation according to the graph partition by executing the operators on the CPU and GPU in parallel. Our experimental results show that the execution time can be reduced by 19.4% at most in the latency-optimal pattern and GPU memory footprint by 67.5% in the memory-optimal pattern compared with the execution on the GPU.

cs.DC↗

arXiv2023

Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging copyright violations, in this paper, we are the first to explore and propose to utilize adversarial examples for DMs to protect human-created artworks. Specifically, we first build a theoretical framework to define and evaluate the adversarial examples for DMs. Then, based on this framework, we design a novel algorithm, named AdvDM, which exploits a Monte-Carlo estimation of adversarial examples for DMs by optimizing upon different latent variables sampled from the reverse process of DMs. Extensive experiments show that the generated adversarial examples can effectively hinder DMs from extracting their features. Therefore, our method can be a powerful tool for human artists to protect their copyright against infringers equipped with DM-based AI-for-Art applications. The code of our method is available on GitHub: https://github.com/mist-project/mist.git.

cs.CV↗