arXiv subjects

Xiang Zhao

Publications and source records attributed to Xiang Zhao.

At least 55 records · Page 3Linked to original sources

arXiv2025

Learning Accurate, Efficient, and Interpretable MLPs on Multiplex Graphs via Node-wise Multi-View Ensemble Distillation

Multiplex graphs, with multiple edge types (graph views) among common nodes, provide richer structural semantics and better modeling capabilities. Multiplex Graph Neural Networks (MGNNs), typically comprising view-specific GNNs and a multi-view integration layer, have achieved advanced performance in various downstream tasks. However, their reliance on neighborhood aggregation poses challenges for deployment in latency-sensitive applications. Motivated by recent GNN-to-MLP knowledge distillation frameworks, we propose Multiplex Graph-Free Neural Networks (MGFNN and MGFNN+) to combine MGNNs' superior performance and MLPs' efficient inference via knowledge distillation. MGFNN directly trains student MLPs with node features as input and soft labels from teacher MGNNs as targets. MGFNN+ further employs a low-rank approximation-based reparameterization to learn node-wise coefficients, enabling adaptive knowledge ensemble from each view-specific GNN. This node-wise multi-view ensemble distillation strategy allows student MLPs to learn more informative multiplex semantic knowledge for different nodes. Experiments show that MGFNNs achieve average accuracy improvements of about 10% over vanilla MLPs and perform comparably or even better to teacher MGNNs (accurate); MGFNNs achieve a 35.40$\times$-89.14$\times$ speedup in inference over MGNNs (efficient); MGFNN+ adaptively assigns different coefficients for multi-view ensemble distillation regarding different nodes (interpretable).

cs.LG↗

arXiv2025

PSSD: Making Large Language Models Self-denial via Human Psyche Structure

The enhance of accuracy in reasoning results of LLMs arouses the community's interests, wherein pioneering studies investigate post-hoc strategies to rectify potential mistakes. Despite extensive efforts, they are all stuck in a state of resource competition demanding significant time and computing expenses. The cause of the situation lies in the failure of identifying the fundamental feature of the solutions in this line, coined as the self-denial of LLMs. In other words, LLMs should confidently determine the potential existence of mistakes and carefully execute the targeted correction. As the whole procedure conducts within LLMs, supporting and persuasive references are hard to acquire, while the absence of specific steps towards refining hidden mistakes persists even when errors are acknowledged. In response to the challenges, we present PSSD, which refers to and implements the human psyche structure such that three distinct and interconnected roles contribute to human reasoning. Specifically, PSSD leverages the recent multi-agent paradigm, and is further enhanced with three innovatively conceived roles: (1) the intuition-based id role that provides initial attempts based on benign LLMs; (2) the rule-driven superego role that summarizes rules to regulate the above attempts, and returns specific key points as guidance; and (3) the script-centric ego role that absorbs all procedural information to generate executable script for the final answer prediction. Extensive experiments demonstrate that the proposed design not only better enhance reasoning capabilities, but also seamlessly integrate with current models, leading to superior performance.

cs.AI↗

arXiv2025

Fusion of Millimeter-wave Radar and Pulse Oximeter Data for Low-burden Diagnosis of Obstructive Sleep Apnea-Hypopnea Syndrome

Objective: The aim of the study is to develop a novel method for improved diagnosis of obstructive sleep apnea-hypopnea syndrome (OSAHS) in clinical or home settings, with the focus on achieving diagnostic performance comparable to the gold-standard polysomnography (PSG) with significantly reduced monitoring burden. Methods: We propose a method using millimeter-wave radar and pulse oximeter for OSAHS diagnosis (ROSA). It contains a sleep apnea-hypopnea events (SAE) detection network, which directly predicts the temporal localization of SAE, and a sleep staging network, which predicts the sleep stages throughout the night, based on radar signals. It also fuses oxygen saturation (SpO2) information from the pulse oximeter to adjust the score of SAE detected by radar. Results: Experimental results on a real-world dataset (>800 hours of overnight recordings, 100 subjects) demonstrated high agreement (ICC=0.9870) on apnea-hypopnea index (AHI) between ROSA and PSG. ROSA also exhibited excellent diagnostic performance, exceeding 90% in accuracy across AHI diagnostic thresholds of 5, 15 and 30 events/h. Conclusion: ROSA improves diagnostic accuracy by fusing millimeter-wave radar and pulse oximeter data. It provides a reliable and low-burden solution for OSAHS diagnosis. Significance: ROSA addresses the limitations of high complexity and monitoring burden associated with traditional PSG. The high accuracy and low burden of ROSA show its potential to improve the accessibility of OSAHS diagnosis among population.

eess.SP↗

arXiv2025

The Expressive Power of Graph Neural Networks: A Survey

Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power. Early works in this domain mainly focus on studying the graph isomorphism recognition ability of GNNs, and recent works try to leverage the properties such as subgraph counting and connectivity learning to characterize the expressive power of GNNs, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for models for enhancing expressive power under different forms of definition. Concretely, the models are reviewed based on three categories, i.e., Graph feature enhancement, Graph topology enhancement, and GNNs architecture enhancement.

cs.LG↗

arXiv2024

Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset \amg, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model \our to achieve multimodal fake news detection and attribution. Experimental results demonstrate that \amg is a challenging dataset, and its attribution setting opens up new avenues for future research.

cs.CL↗

arXiv2024

Logic Induced High-Order Reasoning Network for Event-Event Relation Extraction

To understand a document with multiple events, event-event relation extraction (ERE) emerges as a crucial task, aiming to discern how natural events temporally or structurally associate with each other. To achieve this goal, our work addresses the problems of temporal event relation extraction (TRE) and subevent relation extraction (SRE). The latest methods for such problems have commonly built document-level event graphs for global reasoning across sentences. However, the edges between events are usually derived from external tools heuristically, which are not always reliable and may introduce noise. Moreover, they are not capable of preserving logical constraints among event relations, e.g., coreference constraint, symmetry constraint and conjunction constraint. These constraints guarantee coherence between different relation types,enabling the generation of a uniffed event evolution graph. In this work, we propose a novel method named LogicERE, which performs high-order event relation reasoning through modeling logic constraints. Speciffcally, different from conventional event graphs, we design a logic constraint induced graph (LCG) without any external tools. LCG involves event nodes where the interactions among them can model the coreference constraint, and event pairs nodes where the interactions among them can retain the symmetry constraint and conjunction constraint. Then we perform high-order reasoning on LCG with relational graph transformer to obtain enhanced event and event pair embeddings. Finally, we further incorporate logic constraint information via a joint logic learning module. Extensive experiments demonstrate the effectiveness of the proposed method with state-of-the-art performance on benchmark datasets.

cs.IT↗

arXiv2024

RDPI: A Refine Diffusion Probability Generation Method for Spatiotemporal Data Imputation

Spatiotemporal data imputation plays a crucial role in various fields such as traffic flow monitoring, air quality assessment, and climate prediction. However, spatiotemporal data collected by sensors often suffer from temporal incompleteness, and the sparse and uneven distribution of sensors leads to missing data in the spatial dimension. Among existing methods, autoregressive approaches are prone to error accumulation, while simple conditional diffusion models fail to adequately capture the spatiotemporal relationships between observed and missing data. To address these issues, we propose a novel two-stage Refined Diffusion Probability Impuation (RDPI) framework based on an initial network and a conditional diffusion model. In the initial stage, deterministic imputation methods are used to generate preliminary estimates of the missing data. In the refinement stage, residuals are treated as the diffusion target, and observed values are innovatively incorporated into the forward process. This results in a conditional diffusion model better suited for spatiotemporal data imputation, bridging the gap between the preliminary estimates and the true values. Experiments on multiple datasets demonstrate that RDPI not only achieves state-of-the-art imputation accuracy but also significantly reduces sampling computational costs.

cs.LG↗

arXiv2024

An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms

Question Answering (QA) systems face challenges in handling complex questions that require multi-domain knowledge synthesis. The naive RAG models, although effective in information retrieval, struggle with complex questions that require comprehensive and in-depth answers. The pioneering task is defined as explanatory answer generation, which entails handling identified challenges such as the requirement for comprehensive information and logical coherence within the generated context. To address these issues, we refer to systematic thinking theory and propose SynthRAG, an innovative framework designed to enhance QA performance. SynthRAG improves on conventional models by employing adaptive outlines for dynamic content structuring, generating systematic information to ensure detailed coverage, and producing customized answers tailored to specific user inquiries. This structured approach guarantees logical coherence and thorough integration of information, yielding responses that are both insightful and methodically organized. Empirical evaluations underscore SynthRAG's effectiveness, demonstrating its superiority in handling complex questions, overcoming the limitations of naive RAG models, and significantly improving answer quality and depth. Furthermore, an online deployment on the Zhihu platform revealed that SynthRAG's answers achieved notable user engagement, with each response averaging 5.73 upvotes and surpassing the performance of 79.8% of human contributors, highlighting the practical relevance and impact of the proposed framework. Our code is available at https://github.com/czy1999/SynthRAG .

cs.CL↗

arXiv2024

Programming on Bitcoin: A Survey of Layer 1 and Layer 2 Technologies in Bitcoin Ecosystem

This paper surveys innovative protocols that enhance the programming functionality of the Bitcoin blockchain, a key part of the "Bitcoin Ecosystem." Bitcoin utilizes the Unspent Transaction Output (UTXO) model and a stack-based script language for efficient peer-to-peer payments, but it faces limitations in programming capability and throughput. The 2021 Taproot upgrade introduced the Schnorr signature algorithm and P2TR transaction type, significantly improving Bitcoin's privacy and programming capabilities. This upgrade has led to the development of protocols like Ordinals, Atomicals, and BitVM, which enhance Bitcoin's programming functionality and enrich its ecosystem. We explore the technical aspects of the Taproot upgrade and examine Bitcoin Layer 1 protocols that leverage Taproot's features to program non-fungible tokens (NFTs) into transactions, including Ordinals and Atomicals, along with the fungible token standards BRC-20 and ARC-20. Additionally, we categorize certain Bitcoin ecosystem protocols as Layer 2 solutions similar to Ethereum's, analyzing their impact on Bitcoin's performance. By analyzing data from the Bitcoin blockchain, we gather metrics on block capacity, miner fees, and the growth of Taproot transactions. Our findings confirm the positive effects of these protocols on Bitcoin's mainnet, bridging gaps in the literature regarding Bitcoin's programming capabilities and ecosystem protocols and providing valuable insights for practitioners and researchers.

cs.CR↗

arXiv2024

Calculable neutrino Dirac mass matrix and one-loop $\bar θ$ in the minimal left-right symmetric model

We revisit the contribution to the strong CP parameter $\bar θ$ from leptonic CP violation at one-loop level in the minimal left-right symmetric model in the case of generalized parity as the left-right symmetry. The Hermitian neutrino Dirac mass matrix $M_D$ can be calculated using the light and heavy neutrino masses and mixings. We propose a parametrization of the right-handed neutrino mixing matrix $V_R$ and construct the heavy neutrino mass that maintains the Hermiticity of $M_D$. We further apply it to evaluate the one-loop $\barθ$, denoted as $\bar θ_{loop}$, as a function of the sterile neutrino masses for explicit examples of $V_R$. By requiring the magnitude of $\bar θ_{loop}\lesssim 10^{-10}$, we derive the upper limits on the sterile neutrino masses, which are within reach of direct searches at the Large Hadron Collider and neutrinoless double beta decay experiments. Furthermore, our parametrization is pertinent for other phenomenological investigations.

hep-ph↗

arXiv2024

Temporal Knowledge Question Answering via Abstract Reasoning Induction

In this study, we address the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs). LLMs often struggle with this task, leading to the generation of inaccurate or misleading responses. This issue mainly arises from their limited ability to handle evolving factual knowledge and complex temporal logic. To overcome these limitations, we propose Abstract Reasoning Induction (ARI) framework, which divides temporal reasoning into two distinct phases: Knowledge-agnostic and Knowledge-based. This framework offers factual knowledge support to LLMs while minimizing the incorporation of extraneous noisy data. Concurrently, informed by the principles of constructivism, ARI provides LLMs the capability to engage in proactive, self-directed learning from both correct and incorrect historical reasoning samples. By teaching LLMs to actively construct knowledge and methods, it can significantly boosting their temporal reasoning abilities. Our approach achieves remarkable improvements, with relative gains of 29.7% and 9.27% on two temporal QA datasets, underscoring its efficacy in advancing temporal reasoning in LLMs. The code can be found at https://github.com/czy1999/ARI-QA

cs.CL↗

arXiv2024

Open Knowledge Base Canonicalization with Multi-task Learning

The construction of large open knowledge bases (OKBs) is integral to many knowledge-driven applications on the world wide web such as web search. However, noun phrases and relational phrases in OKBs often suffer from redundancy and ambiguity, which calls for the investigation on OKB canonicalization. Current solutions address OKB canonicalization by devising advanced clustering algorithms and using knowledge graph embedding (KGE) to further facilitate the canonicalization process. Nevertheless, these works fail to fully exploit the synergy between clustering and KGE learning, and the methods designed for these subtasks are sub-optimal. To this end, we put forward a multi-task learning framework, namely MulCanon, to tackle OKB canonicalization. In addition, diffusion model is used in the soft clustering process to improve the noun phrase representations with neighboring information, which can lead to more accurate representations. MulCanon unifies the learning objectives of these sub-tasks, and adopts a two-stage multi-task learning paradigm for training. A thorough experimental study on popular OKB canonicalization benchmarks validates that MulCanon can achieve competitive canonicalization results.

cs.AI↗

arXiv2024

Flat-space Partial Waves From Conformal OPE Densities

We consider the behavior of the OPE density $c(Δ,\ell)$ for conformal four-point functions in the flat-space limit where all scaling dimensions become large. We find evidence that the density reduces to the partial waves $f_\ell(s)$ of the corresponding scattering amplitude. The Euclidean inversion formula then reduces to the partial wave projection and the Lorentzian inversion formula to the Froissart-Gribov formula. The flat-space limit of the OPE density can however also diverge, and we delineate the domain in the complex $s$ plane where this happens. Finally we argue that the conformal dispersion relation reduces to an ordinary single-variable dispersion relation for scattering amplitudes.

hep-th↗

arXiv2024

Complementary LHC searches for UV resonances of the $0νββ$ decay operators

We investigate the quark-level effective operators related to the neutrinoless double beta $(0νββ)$ decay process, and their ultraviolet completions relevant to chiral enhancement effects at the hadronic level. We have classified several kinds of leptoquark models, matching to different standard model effective operators. Assuming weakly-coupled new physics, we find the ongoing $0νββ$-decay experiments are sensitive to new physics scale at around $2\sim 4$ TeV, which is in the reach of LHC searches. We discuss the discovery potential of such resonances in the same-sign dilepton channels at the LHC. Therefore, the direct LHC searches and indirect $0νββ$-decay searches are complementary to each other in testing the UV completions of the effective operators for $0νββ$ decay.

hep-ph↗

arXiv2024

Gravity from quantum mechanics of finite matrices

We revisit the Berenstein-Maldacena-Nastase (BMN) conjecture relating M-theory on a PP-wave background and Matrix Quantum Mechanics (MQM) of $N\times N$ matrices. In particular, we study the BMN MQM at strong coupling and finite $N$ and derive an effective Hamiltonian that describes non-relativistic free particles in a harmonic trap. The energy spectrum predicted by this Hamiltonian matches the supergravity excitation spectrum around the PP-wave background, if we further assume the existence of bound states. Our derivation is based on the strong coupling expansion of the wavefunction and supersedes the naive path integral approach that can lead to incorrect results, as we demonstrate in a simple toy model. We conclude with open questions about various regimes of the theory when we vary the size of the matrices, the coupling and the temperature.

hep-th↗

arXiv2023

GPUSCAN$^{++}$:Efficient Structural Graph Clustering on GPUs

Structural clustering is one of the most popular graph clustering methods, which has achieved great performance improvement by utilizing GPUs. Even though, the state-of-the-art GPU-based structural clustering algorithm, GPUSCAN, still suffers from efficiency issues since lots of extra costs are introduced for parallelization. Moreover, GPUSCAN assumes that the graph is resident in the GPU memory. However, the GPU memory capacity is limited currently while many real-world graphs are big and cannot fit in the GPU memory, which makes GPUSCAN unable to handle large graphs. Motivated by this, we present a new GPU-based structural clustering algorithm, GPUSCAN++, in this paper. To address the efficiency issue, we propose a new progressive clustering method tailored for GPUs that not only avoid high parallelization costs but also fully exploits the computing resources of GPUs. To address the GPU memory limitation issue, we propose a partition-based algorithm for structural clustering that can process large graphs with limited GPU memory. We conduct experiments on real graphs, and the experimental results demonstrate that our algorithm can achieve up to 168 times speedup compared with the state-of-the-art GPU-based algorithm when the graph can be resident in the GPU memory. Moreover, our algorithm is scalable to handle large graphs. As an example, our algorithm can finish the structural clustering on a graph with 1.8 billion edges using less than 2 GB GPU memory.

cs.DB↗

arXiv2023

Open Knowledge Base Canonicalization with Multi-task Unlearning

The construction of large open knowledge bases (OKBs) is integral to many applications in the field of mobile computing. Noun phrases and relational phrases in OKBs often suffer from redundancy and ambiguity, which calls for the investigation on OKB canonicalization. However, in order to meet the requirements of some privacy protection regulations and to ensure the timeliness of the data, the canonicalized OKB often needs to remove some sensitive information or outdated data. The machine unlearning in OKB canonicalization is an excellent solution to the above problem. Current solutions address OKB canonicalization by devising advanced clustering algorithms and using knowledge graph embedding (KGE) to further facilitate the canonicalization process. Effective schemes are urgently needed to fully synergise machine unlearning with clustering and KGE learning. To this end, we put forward a multi-task unlearning framework, namely MulCanon, to tackle machine unlearning problem in OKB canonicalization. Specifically, the noise characteristics in the diffusion model are utilized to achieve the effect of machine unlearning for data in OKB. MulCanon unifies the learning objectives of diffusion model, KGE and clustering algorithms, and adopts a two-step multi-task learning paradigm for training. A thorough experimental study on popular OKB canonicalization datasets validates that MulCanon achieves advanced machine unlearning effects.

cs.AI↗

arXiv2023

A Novel Correlation-optimized Deep Learning Method for Wind Speed Forecast

The increasing installation rate of wind power poses great challenges to the global power system. In order to ensure the reliable operation of the power system, it is necessary to accurately forecast the wind speed and power of the wind turbines. At present, deep learning is progressively applied to the wind speed prediction. Nevertheless, the recent deep learning methods still reflect the embarrassment for practical applications due to model interpretability and hardware limitation. To this end, a novel deep knowledge-based learning method is proposed in this paper. The proposed method hybridizes pre-training method and auto-encoder structure to improve data representation and modeling of the deep knowledge-based learning framework. In order to form knowledge and corresponding absorbers, the original data is preprocessed by an optimization model based on correlation to construct multi-layer networks (knowledge) which are absorbed by sequence to sequence (Seq2Seq) models. Specifically, new cognition and memory units (CMU) are designed to reinforce traditional deep learning framework. Finally, the effectiveness of the proposed method is verified by three wind prediction cases from a wind farm in Liaoning, China. Experimental results show that the proposed method increases the stability and training efficiency compared to the traditional LSTM method and LSTM/GRU-based Seq2Seq method for applications of wind speed forecasting.

cs.LG↗