arXiv subjects

Qiang Wu

Publications and source records attributed to Qiang Wu.

At least 73 records · Page 4Linked to original sources

arXiv2024

Strong Gravitational Lensing by Static Black Holes in Effective Quantum Gravity

We investigate strong gravitational lensing by two static black hole models (Model-1 and Model-2) within the Effective Quantum Gravity (EQG) framework, characterized by mass $M$ and parameter $ζ$. For $ζ= 0$, they reduce to the Schwarzschild solution, and depending on the parameters, they describe black holes with an event and Cauchy horizon (Model-1), a single horizon (Model-2), or no horizons. Using SMBHs Sgr A* and M87* as lenses and integrating theoretical predictions with recent EHT data, we identify significant differences in lensing signatures due to quantum corrections. For Model-1, the deviations of the lensing observables: $|δθ_{\infty}|$ of black holes in EQG from Schwarzschild black hole, for SMBHs Sgr A* and M87, can reach as much as $1.75~μ$as and $1.32~μ$as, while $|δs|$ is about $30.12$~nas for Sgr A* and $22.63$~nas for M87*. The flux ratio of the first image to all subsequent packed images indicates that EQG black hole images are brighter than their Schwarzschild counterparts, with a deviation in the brightness ratio $|δr_{mag}|$ reaching up to 2.02. The time delays between the second and first images, denoted $|δT_{2,1}|$, exhibit substantial deviations from the GR counterpart, reaching up to 1.53 min for Sgr A* and 1159.9 min for M87*. The EHT constraints on $θ_{sh}$ of Sgr A* and M87* within the $1σ$ region limit the parameters $ζ$. Our analysis concludes that EQG black holes are consistent with the EHT observations within this finite space.

astro-ph.CO↗

arXiv2024

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges.

cs.CV↗

arXiv2024

A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine

Large language models (LLMs) and retrieval-augmented generation (RAG) techniques have revolutionized traditional information access, enabling AI agent to search and summarize information on behalf of users during dynamic dialogues. Despite their potential, current AI search engines exhibit considerable room for improvement in several critical areas. These areas include the support for multimodal information, the delivery of personalized responses, the capability to logically answer complex questions, and the facilitation of more flexible interactions. This paper proposes a novel AI Search Engine framework called the Agent Collaboration Network (ACN). The ACN framework consists of multiple specialized agents working collaboratively, each with distinct roles such as Account Manager, Solution Strategist, Information Manager, and Content Creator. This framework integrates mechanisms for picture content understanding, user profile tracking, and online evolution, enhancing the AI search engine's response quality, personalization, and interactivity. A highlight of the ACN is the introduction of a Reflective Forward Optimization method (RFO), which supports the online synergistic adjustment among agents. This feature endows the ACN with online learning capabilities, ensuring that the system has strong interactive flexibility and can promptly adapt to user feedback. This learning method may also serve as an optimization approach for agent-based systems, potentially influencing other domains of agent applications.

cs.IR↗

arXiv2024

Federated User Preference Modeling for Privacy-Preserving Cross-Domain Recommendation

Cross-domain recommendation (CDR) aims to address the data-sparsity problem by transferring knowledge across domains. Existing CDR methods generally assume that the user-item interaction data is shareable between domains, which leads to privacy leakage. Recently, some privacy-preserving CDR (PPCDR) models have been proposed to solve this problem. However, they primarily transfer simple representations learned only from user-item interaction histories, overlooking other useful side information, leading to inaccurate user preferences. Additionally, they transfer differentially private user-item interaction matrices or embeddings across domains to protect privacy. However, these methods offer limited privacy protection, as attackers may exploit external information to infer the original data. To address these challenges, we propose a novel Federated User Preference Modeling (FUPM) framework. In FUPM, first, a novel comprehensive preference exploration module is proposed to learn users' comprehensive preferences from both interaction data and additional data including review texts and potentially positive items. Next, a private preference transfer module is designed to first learn differentially private local and global prototypes, and then privately transfer the global prototypes using a federated learning strategy. These prototypes are generalized representations of user groups, making it difficult for attackers to infer individual information. Extensive experiments on four CDR tasks conducted on the Amazon and Douban datasets validate the superiority of FUPM over SOTA baselines. Code is available at https://github.com/Lili1013/FUPM.

cs.IR↗

arXiv2024

Generalized Estimation and Information

This paper extends the idea of a generalized estimator for a scalar parameter (Vos, 2022) to multi-dimensional parameters both with and without nuisance parameters. The title reflects the fact that generalized estimators provide more than simply another method to find point estimators, and that the methods to assess generalized estimators differ from those for point estimators. By generalized estimation we mean the use of generalized estimators together with an extended definition of information to assess their inferential properties. We show that Fisher information provides an upper bound for the information utilized by an estimator and that the score attains this bound.

math.ST↗

arXiv2024

Theoretical Study on the Structural and Thermodynamic Properties of U-He compounds under High Pressure

Uranium is considered as a very important nuclear energy material because of the huge amount of energy released. As the main products of spontaneous decay of uranium, helium is difficult to react with uranium for its chemical inertness. Therefore, bubbles will be formed inside uranium, which could greatly reduce the performance of uranium or cause the safety problems. Additionally, nuclear materials are usually operated in an environment of high-temperature and high-pressure, so it is necessary to figure out the exact state of helium inside uranium at extreme conditions. Here, we explored the structural stability of U-He system under high-pressure and high-temperature by using density functional theory calculations. Two metastable phases are found between 50 and 400 GPa: U4He with space group Fmmm and U6He with space group P-1. Both are metallic and adopt layered structures. Electron localization function calculation combined with charge density difference analysis indicate that there are covalent bonds between U and U atoms in both Fmmm-U4He and P-1-U6He. Compared with the elastic modulus of $α$-U, the addition of helium has certain influence on the mechanical properties of uranium. Besides, first-principles molecular dynamics simulations were carried out to study the dynamical behavior of Fmmm-U4He and P-1-U6He at high-temperature. It is found that Fmmm-U4He and P-1-U6He undergo one-dimensional superionic phase transitions at 150 GPa. Our study revealed exotic structure of U-He compounds beyond the form of bubble under high-pressure and high-temperature, that might be relevant to the performance and safety issue of nuclear materials at extreme conditions.

cond-mat.mtrl-sci↗

arXiv2024

Multiobjective Vehicle Routing Optimization with Time Windows: A Hybrid Approach Using Deep Reinforcement Learning and NSGA-II

This paper proposes a weight-aware deep reinforcement learning (WADRL) approach designed to address the multiobjective vehicle routing problem with time windows (MOVRPTW), aiming to use a single deep reinforcement learning (DRL) model to solve the entire multiobjective optimization problem. The Non-dominated sorting genetic algorithm-II (NSGA-II) method is then employed to optimize the outcomes produced by the WADRL, thereby mitigating the limitations of both approaches. Firstly, we design an MOVRPTW model to balance the minimization of travel cost and the maximization of customer satisfaction. Subsequently, we present a novel DRL framework that incorporates a transformer-based policy network. This network is composed of an encoder module, a weight embedding module where the weights of the objective functions are incorporated, and a decoder module. NSGA-II is then utilized to optimize the solutions generated by WADRL. Finally, extensive experimental results demonstrate that our method outperforms the existing and traditional methods. Due to the numerous constraints in VRPTW, generating initial solutions of the NSGA-II algorithm can be time-consuming. However, using solutions generated by the WADRL as initial solutions for NSGA-II significantly reduces the time required for generating initial solutions. Meanwhile, the NSGA-II algorithm can enhance the quality of solutions generated by WADRL, resulting in solutions with better scalability. Notably, the weight-aware strategy significantly reduces the training time of DRL while achieving better results, enabling a single DRL model to solve the entire multiobjective optimization problem.

cs.AI↗

arXiv2024

Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems

Retrieval-augmented generation (RAG) techniques leverage the in-context learning capabilities of large language models (LLMs) to produce more accurate and relevant responses. Originating from the simple 'retrieve-then-read' approach, the RAG framework has evolved into a highly flexible and modular paradigm. A critical component, the Query Rewriter module, enhances knowledge retrieval by generating a search-friendly query. This method aligns input questions more closely with the knowledge base. Our research identifies opportunities to enhance the Query Rewriter module to Query Rewriter+ by generating multiple queries to overcome the Information Plateaus associated with a single query and by rewriting questions to eliminate Ambiguity, thereby clarifying the underlying intent. We also find that current RAG systems exhibit issues with Irrelevant Knowledge; to overcome this, we propose the Knowledge Filter. These two modules are both based on the instruction-tuned Gemma-2B model, which together enhance response quality. The final identified issue is Redundant Retrieval; we introduce the Memory Knowledge Reservoir and the Retriever Trigger to solve this. The former supports the dynamic expansion of the RAG system's knowledge base in a parameter-free manner, while the latter optimizes the cost for accessing external knowledge, thereby improving resource utilization and response efficiency. These four RAG modules synergistically improve the response quality and efficiency of the RAG system. The effectiveness of these modules has been validated through experiments and ablation studies across six common QA datasets. The source code can be accessed at https://github.com/Ancientshi/ERM4.

cs.CL↗

arXiv2024

Hypergraph Counting and Mixed $p$-Spin Glass Models under Replica Symmetry

We study the fluctuation problems at high temperature in the general mixed $p$-spin glass models under the weak external field assumption: $h= ρN^{-α}, ρ>0, α\in [1/4,\infty]$. By extending the cluster expansion approach to this generic setting, we convert the fluctuation problem as a hypergraph counting problem and thus obtain a new multiple-transition phenomenon. A by-product of our results is a new critical inverse temperature obtained from optimal second moment estimates. In particular, all our fluctuation results hold up to the threshold. Combining with multivariate Stein's method, we also obtain an explicit convergence rate under proper moment assumptions on the general symmetric disorder. Our results have several further implications. First, our approach works for both even and odd pure $p$-spin models. The leading cluster structures in the odd $p$ case are different and more involved than in the even $p$ case. This combinatorially explains the folklore that odd $p$-spin is more complicated than even $p$. Second, in the mixed $p$-spin setting, the cluster structures differ depending on the relation between the minimum effective even and odd $p$-spins: $p_e$ and $p_o$. As an example, at $h=0$, there are three sub-regimes: $p_e<p_o, p_o<p_e<2p_o, p_e\ge 2p_o$, wherein the first and third ones, the mixed model behaves essentially like a pure $p$-spin model, and only in the second regime, it is more like a mixture. This gives another criterion for classifying mean-field spin glass models compared to the work of Auffinger and Ben Arous (Ann.~Probab.~41 (2013), no.~6, 4214--4247), where the idea is based on complexity computations for spherical models. Third, our framework naturally implies a multi-scale fluctuation phenomenon conjectured in the work of Bovier and Schertzer (Probab. Theory Relat. Fields (2024)).

math.PR↗

arXiv2024

PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization

Quantization is one of the most effective methods to compress neural networks, which has achieved great success on convolutional neural networks (CNNs). Recently, vision transformers have demonstrated great potential in computer vision. However, previous post-training quantization methods performed not well on vision transformer, resulting in more than 1% accuracy drop even in 8-bit quantization. Therefore, we analyze the problems of quantization on vision transformers. We observe the distributions of activation values after softmax and GELU functions are quite different from the Gaussian distribution. We also observe that common quantization metrics, such as MSE and cosine distance, are inaccurate to determine the optimal scaling factor. In this paper, we propose the twin uniform quantization method to reduce the quantization error on these activation values. And we propose to use a Hessian guided metric to evaluate different scaling factors, which improves the accuracy of calibration at a small cost. To enable the fast quantization of vision transformers, we develop an efficient framework, PTQ4ViT. Experiments show the quantized vision transformers achieve near-lossless prediction accuracy (less than 0.5% drop at 8-bit quantization) on the ImageNet classification task.

cs.CV↗

arXiv2024

Conditional Local Feature Encoding for Graph Neural Networks

Graph neural networks (GNNs) have shown great success in learning from graph-based data. The key mechanism of current GNNs is message passing, where a node's feature is updated based on the information passing from its local neighbourhood. A limitation of this mechanism is that node features become increasingly dominated by the information aggregated from the neighbourhood as we use more rounds of message passing. Consequently, as the GNN layers become deeper, adjacent node features tends to be similar, making it more difficult for GNNs to distinguish adjacent nodes, thereby, limiting the performance of GNNs. In this paper, we propose conditional local feature encoding (CLFE) to help prevent the problem of node features being dominated by the information from local neighbourhood. The idea of our method is to extract the node hidden state embedding from message passing process and concatenate it with the nodes feature from previous stage, then we utilise linear transformation to form a CLFE based on the concatenated vector. The CLFE will form the layer output to better preserve node-specific information, thus help to improve the performance of GNN models. To verify the feasibility of our method, we conducted extensive experiments on seven benchmark datasets for four graph domain tasks: super-pixel graph classification, node classification, link prediction, and graph regression. The experimental results consistently demonstrate that our method improves model performance across a variety of baseline GNN models for all four tasks.

cs.LG↗

arXiv2024

ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization

Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has evolved into a more extended process due to the integration of various components, sometimes even forming loop structures. Despite its advancements in improving response accuracy, challenges like poor retrieval quality for complex questions that require the search of multifaceted semantic information, inefficiencies in knowledge re-retrieval during long-term serving, and lack of personalized responses persist. Motivated by transcending these limitations, we introduce ERAGent, a cutting-edge framework that embodies an advancement in the RAG area. Our contribution is the introduction of the synergistically operated module: Enhanced Question Rewriter and Knowledge Filter, for better retrieval quality. Retrieval Trigger is incorporated to curtail extraneous external knowledge retrieval without sacrificing response quality. ERAGent also personalizes responses by incorporating a learned user profile. The efficiency and personalization characteristics of ERAGent are supported by the Experiential Learner module which makes the AI assistant being capable of expanding its knowledge and modeling user profile incrementally. Rigorous evaluations across six datasets and three question-answering tasks prove ERAGent's superior accuracy, efficiency, and personalization, emphasizing its potential to advance the RAG field and its applicability in practical systems.

cs.CL↗

arXiv2024

DST-GTN: Dynamic Spatio-Temporal Graph Transformer Network for Traffic Forecasting

Accurate traffic forecasting is essential for effective urban planning and congestion management. Deep learning (DL) approaches have gained colossal success in traffic forecasting but still face challenges in capturing the intricacies of traffic dynamics. In this paper, we identify and address this challenges by emphasizing that spatial features are inherently dynamic and change over time. A novel in-depth feature representation, called Dynamic Spatio-Temporal (Dyn-ST) features, is introduced, which encapsulates spatial characteristics across varying times. Moreover, a Dynamic Spatio-Temporal Graph Transformer Network (DST-GTN) is proposed by capturing Dyn-ST features and other dynamic adjacency relations between intersections. The DST-GTN can model dynamic ST relationships between nodes accurately and refine the representation of global and local ST characteristics by adopting adaptive weights in low-pass and all-pass filters, enabling the extraction of Dyn-ST features from traffic time-series data. Through numerical experiments on public datasets, the DST-GTN achieves state-of-the-art performance for a range of traffic forecasting tasks and demonstrates enhanced stability.

cs.AI↗

arXiv2024

Central Limit Theorem of Overlap for the Mean Field Ghatak-Sherrington model

The Ghatak-Sherrington (GS) spin glass model is a random probability measure defined on the configuration space $\{0,\pm1,\pm2,\ldots, \pm \mathcal{S} \}^N$ with system size $N$ and $\mathcal{S}\ge1$ finite. This generalizes the classical Sherrington-Kirkpatrick (SK) model on the boolean cube $\{-1,+1\}^N$ in order to capture more complex behaviors, including the spontaneous inverse freezing phenomenon. Although many results on the physics side have been established to understand the GS model, mathematical exploration of the model remains scarce. Overlap, the normalized inner product of two configurations, acts as the system order parameter to understand the phase transition of mean-field spin glass models. In this paper, we use moment method combined with the cavity approach to rigorously establish a quantitative joint central limit theorem for the overlap and self-overlap array. The results hold at high temperatures under arbitrary crystal and external fields. Compared to the SK model, the main challenge comes from the non-trivial self-overlap terms which also correlated with the standard overlap terms.

math.PR↗

arXiv2024

Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation

Social recommendation systems face the problem of social influence bias, which can lead to an overemphasis on recommending items that friends have interacted with. Addressing this problem is crucial, and existing methods often rely on techniques such as weight adjustment or leveraging unbiased data to eliminate this bias. However, we argue that not all biases are detrimental, i.e., some items recommended by friends may align with the user's interests. Blindly eliminating such biases could undermine these positive effects, potentially diminishing recommendation accuracy. In this paper, we propose a Causal Disentanglement-based framework for Regulating Social influence Bias in social recommendation, named CDRSB, to improve recommendation performance. From the perspective of causal inference, we find that the user social network could be regarded as a confounder between the user and item embeddings (treatment) and ratings (outcome). Due to the presence of this social network confounder, two paths exist from user and item embeddings to ratings: a non-causal social influence path and a causal interest path. Building upon this insight, we propose a disentangled encoder that focuses on disentangling user and item embeddings into interest and social influence embeddings. Mutual information-based objectives are designed to enhance the distinctiveness of these disentangled embeddings, eliminating redundant information. Additionally, a regulatory decoder that employs a weight calculation module to dynamically learn the weights of social influence embeddings for effectively regulating social influence bias has been designed. Experimental results on four large-scale real-world datasets Ciao, Epinions, Dianping, and Douban book demonstrate the effectiveness of CDRSB compared to state-of-the-art baselines.

cs.SI↗

arXiv2024

A Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation

Cross-domain recommendation (CDR) aims to enhance recommendation accuracy in a target domain with sparse data by leveraging rich information in a source domain, thereby addressing the data-sparsity problem. Some existing CDR methods highlight the advantages of extracting domain-common and domain-specific features to learn comprehensive user and item representations. However, these methods can't effectively disentangle these components as they often rely on simple user-item historical interaction information (such as ratings, clicks, and browsing), neglecting the rich multi-modal features. Additionally, they don't protect user-sensitive data from potential leakage during knowledge transfer between domains. To address these challenges, we propose a Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation, called P2M2-CDR. Specifically, we first design a multi-modal disentangled encoder that utilizes multi-modal information to disentangle more informative domain-common and domain-specific embeddings. Furthermore, we introduce a privacy-preserving decoder to mitigate user privacy leakage during knowledge transfer. Local differential privacy (LDP) is utilized to obfuscate the disentangled embeddings before inter-domain exchange, thereby enhancing privacy protection. To ensure both consistency and differentiation among these obfuscated disentangled embeddings, we incorporate contrastive learning-based domain-inter and domain-intra losses. Extensive Experiments conducted on four real-world datasets demonstrate that P2M2-CDR outperforms other state-of-the-art single-domain and cross-domain baselines.

cs.AI↗

arXiv2024

All-optical polarization scrambler based on polarization beam splitting with amplified fiber ring

Optical-fiber-based polarization scramblers can reduce the impact of polarization sensitive performance of various optical fiber systems. Here, we propose a simple and efficient polarization scrambler based on an all optical Mach-Zehnder structure by combining polarization beam splitter and amplified fiber ring. To totally decoherence one polarization splitted beam, a fiber ring together with an amplifier are incorporated. The ratio of two orthogonal beams can be controlled by varying the amplification factor, and we observe different evolution trajectories of the output state of polarizations on Poincare sphere. When the amplification factor exceeds a certain threshold, the scrambler system exhibits chaotical behavior. A commercial single wavelength laser with linewidth of 3 MHz is utilized to characterize the scrambling performance. We found that when the sampling rate is 1.6 MSa/s, a scrambling speed up to 2000 krad/s can be obtained for the average degree of polarization being less than 0.1. We also exploit these chaotic polarization fluctuations to generate random binary number, indicating that the proposed technique is a good candidate for random bit generator.

physics.optics↗

arXiv2024

Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes

Despite the recent successes of vanilla Graph Neural Networks (GNNs) on various tasks, their foundation on pairwise networks inherently limits their capacity to discern latent higher-order interactions in complex systems. To bridge this capability gap, we propose a novel approach exploiting the rich mathematical theory of simplicial complexes (SCs) - a robust tool for modeling higher-order interactions. Current SC-based GNNs are burdened by high complexity and rigidity, and quantifying higher-order interaction strengths remains challenging. Innovatively, we present a higher-order Flower-Petals (FP) model, incorporating FP Laplacians into SCs. Further, we introduce a Higher-order Graph Convolutional Network (HiGCN) grounded in FP Laplacians, capable of discerning intrinsic features across varying topological scales. By employing learnable graph filters, a parameter group within each FP Laplacian domain, we can identify diverse patterns where the filters' weights serve as a quantifiable measure of higher-order interaction strengths. The theoretical underpinnings of HiGCN's advanced expressiveness are rigorously demonstrated. Additionally, our empirical investigations reveal that the proposed model accomplishes state-of-the-art performance on a range of graph tasks and provides a scalable and flexible solution to explore higher-order interactions in graphs. Codes and datasets are available at https://github.com/Yiminghh/HiGCN.

cs.LG↗