arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 613 records · Page 34Linked to original sources

arXiv2024

Decision-making with Speculative Opponent Models

Opponent modelling has proven effective in enhancing the decision-making of the controlled agent by constructing models of opponent agents. However, existing methods often rely on access to the observations and actions of opponents, a requirement that is infeasible when such information is either unobservable or challenging to obtain. To address this issue, we introduce Distributional Opponent-aided Multi-agent Actor-Critic (DOMAC), the first speculative opponent modelling algorithm that relies solely on local information (i.e., the controlled agent's observations, actions, and rewards). Specifically, the actor maintains a speculated belief about the opponents using the tailored speculative opponent models that predict the opponents' actions using only local information. Moreover, DOMAC features distributional critic models that estimate the return distribution of the actor's policy, yielding a more fine-grained assessment of the actor's quality. This thus more effectively guides the training of the speculative opponent models that the actor depends upon. Furthermore, we formally derive a policy gradient theorem with the proposed opponent models. Extensive experiments under eight different challenging multi-agent benchmark tasks within the MPE, Pommerman and StarCraft Multiagent Challenge (SMAC) demonstrate that our DOMAC successfully models opponents' behaviours and delivers superior performance against state-of-the-art methods with a faster convergence speed.

cs.AI↗

arXiv2024

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation. Despite these benefits, the efficiency of synthetic data generated by current methodologies remains inferior when training advanced deep models exclusively, limiting its practical utility. To address this challenge, we analyze the principles underlying training data synthesis for supervised learning and elucidate a principled theoretical framework from the distribution-matching perspective that explicates the mechanisms governing synthesis efficacy. Through extensive experiments, we demonstrate the effectiveness of our synthetic data across diverse image classification tasks, both as a replacement for and augmentation to real datasets, while also benefits such as out-of-distribution generalization, privacy preservation, and scalability. Specifically, we achieve 70.9% top1 classification accuracy on ImageNet1K when training solely with synthetic data equivalent to 1 X the original real data size, which increases to 76.0% when scaling up to 10 X synthetic data.

cs.LG↗

arXiv2024

iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching

We present a method named iComMa to address the 6D camera pose estimation problem in computer vision. Conventional pose estimation methods typically rely on the target's CAD model or necessitate specific network training tailored to particular object classes. Some existing methods have achieved promising results in mesh-free object and scene pose estimation by inverting the Neural Radiance Fields (NeRF). However, they still struggle with adverse initializations such as large rotations and translations. To address this issue, we propose an efficient method for accurate camera pose estimation by inverting 3D Gaussian Splatting (3DGS). Specifically, a gradient-based differentiable framework optimizes camera pose by minimizing the residual between the query image and the rendered image, requiring no training. An end-to-end matching module is designed to enhance the model's robustness against adverse initializations, while minimizing pixel-level comparing loss aids in precise pose estimation. Experimental results on synthetic and complex real-world data demonstrate the effectiveness of the proposed approach in challenging conditions and the accuracy of camera pose estimation.

cs.CV↗

arXiv2024

The long-term evolution of the GW170817 remnant

GW170817 represents the first observed binary neutron star merger event by humanity. The observation of GW170817 has identified the correlation between Kilonova, gravitational wave and short GRB. The shocks from GW170817 have the capacity to inject significant thermal and kinetic energies into the interstellar medium and evolve for over a million years. In this letter, we adopt the special relativity fluid dynamics equations to simulate the evolution of the GW170817 remnant over a span of one million years. Our simulations yield the evolution profiles of the velocity, density, mass, radius, luminosity, and energies of the remnant. We estimate that the GW170817 remnant will reach the average maximum luminosity $ 2.56\times 10^{39}$ erg s$^{-1}$at approximately $3.96\times 10^4$ yr. At the end of the cooling stage, the contaminated radius and mass are $48.35$ pc and $2.25\times 10^4 M_{\odot}$, respectively.

astro-ph.HE↗

arXiv2024

Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators

Federated learning has become a popular method to learn from decentralized heterogeneous data. Federated semi-supervised learning (FSSL) emerges to train models from a small fraction of labeled data due to label scarcity on decentralized clients. Existing FSSL methods assume independent and identically distributed (IID) labeled data across clients and consistent class distribution between labeled and unlabeled data within a client. This work studies a more practical and challenging scenario of FSSL, where data distribution is different not only across clients but also within a client between labeled and unlabeled data. To address this challenge, we propose a novel FSSL framework with dual regulators, FedDure. FedDure lifts the previous assumption with a coarse-grained regulator (C-reg) and a fine-grained regulator (F-reg): C-reg regularizes the updating of the local model by tracking the learning effect on labeled data distribution; F-reg learns an adaptive weighting scheme tailored for unlabeled instances in each client. We further formulate the client model training as bi-level optimization that adaptively optimizes the model in the client with two regulators. Theoretically, we show the convergence guarantee of the dual regulators. Empirically, we demonstrate that FedDure is superior to the existing methods across a wide range of settings, notably by more than 11 on CIFAR-10 and CINIC-10 datasets.

cs.LG↗

arXiv2024

DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning

Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data, and federated domain generalization further considers the test dataset (target domain) is absent from the decentralized training data (source domains). However, most existing FL methods assume that domain labels are provided during training, and their evaluation imposes explicit constraints on the number of domains, which must strictly match the number of clients. Because of the underutilization of numerous edge devices and additional cross-client domain annotations in the real world, such restrictions may be impractical and involve potential privacy leaks. In this paper, we propose an efficient and novel approach, called Disentangled Prompt Tuning (DiPrompT), a method that tackles the above restrictions by learning adaptive prompts for domain generalization in a distributed manner. Specifically, we first design two types of prompts, i.e., global prompt to capture general knowledge across all clients and domain prompts to capture domain-specific knowledge. They eliminate the restriction on the one-to-one mapping between source domains and local clients. Furthermore, a dynamic query metric is introduced to automatically search the suitable domain label for each sample, which includes two-substep text-image alignments based on prompt tuning without labor-intensive annotation. Extensive experiments on multiple datasets demonstrate that our DiPrompT achieves superior domain generalization performance over state-of-the-art FL methods when domain labels are not provided, and even outperforms many centralized learning methods using domain labels.

cs.LG↗

arXiv2024

Pan-Mamba: Effective pan-sharpening with State Space Model

Pan-sharpening involves integrating information from low-resolution multi-spectral and high-resolution panchromatic images to generate high-resolution multi-spectral counterparts. While recent advancements in the state space model, particularly the efficient long-range dependency modeling achieved by Mamba, have revolutionized computer vision community, its untapped potential in pan-sharpening motivates our exploration. Our contribution, Pan-Mamba, represents a novel pan-sharpening network that leverages the efficiency of the Mamba model in global information modeling. In Pan-Mamba, we customize two core components: channel swapping Mamba and cross-modal Mamba, strategically designed for efficient cross-modal information exchange and fusion. The former initiates a lightweight cross-modal interaction through the exchange of partial panchromatic and multi-spectral channels, while the latter facilities the information representation capability by exploiting inherent cross-modal relationships. Through extensive experiments across diverse datasets, our proposed approach surpasses state-of-the-art methods, showcasing superior fusion results in pan-sharpening. To the best of our knowledge, this work is the first attempt in exploring the potential of the Mamba model and establishes a new frontier in the pan-sharpening techniques. The source code is available at \url{https://github.com/alexhe101/Pan-Mamba}.

cs.CV↗

arXiv2024

Cycle-factors in oriented graphs

Let $k$ be a positive integer. A $k$-cycle-factor of an oriented graph is a set of disjoint cycles of length $k$ that covers all vertices of the graph. In this paper, we prove that there exists a positive constant $c$ such that for $n$ sufficiently large, any oriented graph on $n$ vertices with both minimum out-degree and minimum in-degree at least $(1/2-c)n$ contains a $k$-cycle-factor for any $k\geq4$. Additionally, under the same hypotheses, we also show that for any sequence $n_1, \ldots, n_t$ with $\sum^t_{i=1}n_i=n$ and the number of the $n_i$ equal to $3$ is $αn$, where $α$ is any real number with $0<α<1/3$, the oriented graph contains $t$ disjoint cycles of lengths $n_1, \ldots, n_t$. This conclusion is the best possible in some sense and refines a result of Keevash and Sudakov.

math.CO↗

arXiv2024

Mode-resolved thermometry of trapped ion with Deep Learning

In trapped ion system, accurate thermometry of ion is crucial for evaluating the system state and precisely performing quantum operations. However, when the motional state of a single ion is far away from the ground state, the spatial dimension of the phonon state sharply increases, making it difficult to realize accurate and mode-resolved thermometry with existing methods. In this work, we apply deep learning for the first time to the thermometry of trapped ion, providing an efficient and mode-resolved method for accurately estimating large mean phonon numbers. Our trained neural network model can be directly applied to other experimental setups without retraining or post-processing, as long as the related parameters are covered by the model's effective range, and it can also be conveniently extended to other parameter ranges. We have conducted experimental verification based on our surface trap, of which the result has shown the accuracy and efficiency of the method for thermometry of single ion under large mean phonon number, and its mode resolution characteristic can make it better applied to the characterization of system parameters, such as evaluating cooling effectiveness, analyzing surface trap noise.

quant-ph↗

arXiv2024

RSAM-Seg: A SAM-based Approach with Prior Knowledge Integration for Remote Sensing Image Semantic Segmentation

The development of high-resolution remote sensing satellites has provided great convenience for research work related to remote sensing. Segmentation and extraction of specific targets are essential tasks when facing the vast and complex remote sensing images. Recently, the introduction of Segment Anything Model (SAM) provides a universal pre-training model for image segmentation tasks. While the direct application of SAM to remote sensing image segmentation tasks does not yield satisfactory results, we propose RSAM-Seg, which stands for Remote Sensing SAM with Semantic Segmentation, as a tailored modification of SAM for the remote sensing field and eliminates the need for manual intervention to provide prompts. Adapter-Scale, a set of supplementary scaling modules, are proposed in the multi-head attention blocks of the encoder part of SAM. Furthermore, Adapter-Feature are inserted between the Vision Transformer (ViT) blocks. These modules aim to incorporate high-frequency image information and image embedding features to generate image-informed prompts. Experiments are conducted on four distinct remote sensing scenarios, encompassing cloud detection, field monitoring, building detection and road mapping tasks . The experimental results not only showcase the improvement over the original SAM and U-Net across cloud, buildings, fields and roads scenarios, but also highlight the capacity of RSAM-Seg to discern absent areas within the ground truth of certain datasets, affirming its potential as an auxiliary annotation method. In addition, the performance in few-shot scenarios is commendable, underscores its potential in dealing with limited datasets.

cs.CV↗

arXiv2024

Adaptive Perturbation for Adversarial Attack

In recent years, the security of deep learning models achieves more and more attentions with the rapid development of neural networks, which are vulnerable to adversarial examples. Almost all existing gradient-based attack methods use the sign function in the generation to meet the requirement of perturbation budget on $L_\infty$ norm. However, we find that the sign function may be improper for generating adversarial examples since it modifies the exact gradient direction. Instead of using the sign function, we propose to directly utilize the exact gradient direction with a scaling factor for generating adversarial perturbations, which improves the attack success rates of adversarial examples even with fewer perturbations. At the same time, we also theoretically prove that this method can achieve better black-box transferability. Moreover, considering that the best scaling factor varies across different images, we propose an adaptive scaling factor generator to seek an appropriate scaling factor for each image, which avoids the computational cost for manually searching the scaling factor. Our method can be integrated with almost all existing gradient-based attack methods to further improve their attack success rates. Extensive experiments on the CIFAR10 and ImageNet datasets show that our method exhibits higher transferability and outperforms the state-of-the-art methods.

cs.CV↗

arXiv2024

Characterizing the spatial potential of a surface electrode ion trap

The accurate characterization of the spatial potential generated by a planar electrode in a surface-type Paul trap is of great interest. To achieve this, we employ a simple yet highly precise parametric expression to describe the spatial field of a rectangular-shaped electrode. Based on this, an optimization method is introduced to precisely characterize the axial electric field intensity created by the powered electrode and the stray field. In contrast to existing methods, various types of experimental data, such as the equilibrium position of ions in a linear string, equilibrium positions of single trapped ions and trap frequencies, are utilized for potential estimation in order to mitigate systematic errors. This approach offers significant flexibility in voltage settings for data collection, making it particularly well-suited for surface electrode traps where ion probe trapping height may vary with casual voltage settings. In our demonstration, we successfully minimized the discrepancy between experimental observations and model predictions to an impressive extent. The relative errors of secular frequencies were suppressed within $\pm$ 0.5$\%$, and the positional error of ions was limited to less than 1.2 $μ$m, all surpassing those achieved by existing methodologies.

quant-ph↗

arXiv2024

Ultrafast and precise distance measurement via real-time chirped pulse interferometry

Laser frequency combs, which are composed of a series of equally-spaced coherent frequency components, have triggered revolutionary progress for precision spectroscopy and optical metrology. Length/distance is of fundamental importance in both science and technology. In this work, we describe a ranging scheme based on chirped pulse interferometry. In contrast to the traditional spectral interferometry, the local oscillator is strongly chirped which is able to meet the measurement pulses at arbitrary distances, and therefore the dead zones can be removed. The distances can be precisely determined via two measurement steps based on time-of-flight method and synthetic wavelength interferometry, respectively. To overcome the speed limitation of the optical spectrum analyzer, the spectrograms are stretched and detected by a fast photodetector and oscilloscope, and consequently mapped into the time domain in real time. The experimental results indicate that the measurement uncertainty can be well within 2 $\upmu$m, compared with the reference distance meter. The Allan deviation can reach 0.4 $\upmu$m at averaging time of 4 ns, 25 nm at 1 $\upmu$s, and can achieve 2 nm at 100 $\upmu$s averaging time. We also measure a spinning disk with grooves of different depths to verify the measurement speed, and the results show that the grooves with about 150 m/s line speed can be clearly captured. Our method provides a unique combination of non-dead zones, ultrafast measurement speed, high precision and accuracy, large ambiguity range, and with only one single comb source. This system could offer a powerful solution for the field measurements in practical applications in future.

physics.optics↗

arXiv2024

On Truthful Item-Acquiring Mechanisms for Reward Maximization

In this research, we study the problem that a collector acquires items from the owner based on the item qualities the owner declares and an independent appraiser's assessments. The owner is interested in maximizing the probability that the collector acquires the items and is the only one who knows the items' factual quality. The appraiser performs her duties with impartiality, but her assessment may be subject to random noises, so it may not accurately reflect the factual quality of the items. The main challenge lies in devising mechanisms that prompt the owner to reveal accurate information, thereby optimizing the collector's expected reward. We consider the menu size of mechanisms as a measure of their practicability and study its impact on the attainable expected reward. For the single-item setting, we design optimal mechanisms with a monotone increasing menu size. Although the reward gap between the simplest and optimal mechanisms is bounded, we show that simple mechanisms with a small menu size cannot ensure any positive fraction of the optimal reward of mechanisms with a larger menu size. For the multi-item setting, we show that an ordinal mechanism that only takes the owner's ordering of the items as input is not incentive-compatible. We then propose a set of Union mechanisms that combine single-item mechanisms. Moreover, we run experiments to examine these mechanisms' robustness against the independent appraiser's assessment accuracy and the items' acquiring rate.

cs.GT↗

arXiv2024

FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing

Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer structure and are highly redundant. These linear layers contribute more than 80% of the computation workload and 99% of the model size. To pretrain and finetune LLMs efficiently, there are three major challenges to address: 1) reducing redundancy of the linear layers; 2) reducing GPU memory footprint; 3) improving GPU utilization when using distributed training. Prior methods, such as LoRA and QLoRA, utilized low-rank matrices and quantization to reduce the number of trainable parameters and model size, respectively. However, the resulting model still consumes a large amount of GPU memory. In this paper, we present high-performance GPU-based methods that exploit low-rank structures to pretrain and finetune LLMs for financial applications. We replace one conventional linear layer of the transformer structure with two narrower linear layers, which allows us to reduce the number of parameters by several orders of magnitude. By quantizing the parameters into low precision (8-bit and 4-bit), the memory consumption of the resulting model is further reduced. Compared with existing LLMs, our methods achieve a speedup of 1.3X and a model compression ratio of 2.64X for pretaining without accuracy drop. For finetuning, our methods achieve an average accuracy increase of 6.3% and 24.0% in general tasks and financial tasks, respectively, and GPU memory consumption ratio of 6.3X. The sizes of our models are smaller than 0.59 GB, allowing inference on a smartphone.

cs.LG↗

arXiv2024

Towards Cross-Domain Continual Learning

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks efficiently, while avoiding catastrophic forgetting. Existing methods primarily focus on single domains, restricting their applicability to specific problems. In this work, we introduce a novel approach called Cross-Domain Continual Learning (CDCL) that addresses the limitations of being limited to single supervised domains. Our method combines inter- and intra-task cross-attention mechanisms within a compact convolutional network. This integration enables the model to maintain alignment with features from previous tasks, thereby delaying the data drift that may occur between tasks, while performing unsupervised cross-domain (UDA) between related domains. By leveraging an intra-task-specific pseudo-labeling method, we ensure accurate input pairs for both labeled and unlabeled samples, enhancing the learning process. To validate our approach, we conduct extensive experiments on public UDA datasets, showcasing its positive performance on cross-domain continual learning challenges. Additionally, our work introduces incremental ideas that contribute to the advancement of this field. We make our code and models available to encourage further exploration and reproduction of our results: \url{https://github.com/Ivsucram/CDCL}

cs.LG↗

arXiv2024

Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling

Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics. However, their performance is still far from optimality, mainly because the underlying graph representation scheme is unsuitable for modelling partial solutions at each construction step. This paper proposes a novel DRL-guided improvement heuristic for solving JSSP, where graph representation is employed to encode complete solutions. We design a Graph Neural-Network-based representation scheme, consisting of two modules to effectively capture the information of dynamic topology and different types of nodes in graphs encountered during the improvement process. To speed up solution evaluation during improvement, we present a novel message-passing mechanism that can evaluate multiple solutions simultaneously. We prove that the computational complexity of our method scales linearly with problem size. Experiments on classic benchmarks show that the improvement policy learned by our method outperforms state-of-the-art DRL-based methods by a large margin.

cs.LG↗

arXiv2024

Large Language Model with Graph Convolution for Recommendation

In recent years, efforts have been made to use text information for better user profiling and item characterization in recommendations. However, text information can sometimes be of low quality, hindering its effectiveness for real-world applications. With knowledge and reasoning capabilities capsuled in Large Language Models (LLMs), utilizing LLMs emerges as a promising way for description improvement. However, existing ways of prompting LLMs with raw texts ignore structured knowledge of user-item interactions, which may lead to hallucination problems like inconsistent description generation. To this end, we propose a Graph-aware Convolutional LLM method to elicit LLMs to capture high-order relations in the user-item graph. To adapt text-based LLMs with structured graphs, We use the LLM as an aggregator in graph processing, allowing it to understand graph-based information step by step. Specifically, the LLM is required for description enhancement by exploring multi-hop neighbors layer by layer, thereby propagating information progressively in the graph. To enable LLMs to capture large-scale graph information, we break down the description task into smaller parts, which drastically reduces the context length of the token input with each step. Extensive experiments on three real-world datasets show that our method consistently outperforms state-of-the-art methods.

cs.AI↗