arXiv subjects

Meng Xiao

Publications and source records attributed to Meng Xiao.

At least 55 records · Page 3Linked to original sources

arXiv2025

Towards Data-Centric AI: A Comprehensive Survey of Traditional, Reinforcement, and Generative Approaches for Tabular Data Transformation

Tabular data is one of the most widely used formats across industries, driving critical applications in areas such as finance, healthcare, and marketing. In the era of data-centric AI, improving data quality and representation has become essential for enhancing model performance, particularly in applications centered around tabular data. This survey examines the key aspects of tabular data-centric AI, emphasizing feature selection and feature generation as essential techniques for data space refinement. We provide a systematic review of feature selection methods, which identify and retain the most relevant data attributes, and feature generation approaches, which create new features to simplify the capture of complex data patterns. This survey offers a comprehensive overview of current methodologies through an analysis of recent advancements, practical applications, and the strengths and limitations of these techniques. Finally, we outline open challenges and suggest future perspectives to inspire continued innovation in this field.

cs.LG↗

arXiv2025

Janus Bound States in the Continuum with Asymmetric Topological Charges

We propose a novel topological defect called Janus bound states in the continuum (BICs), featuring asymmetric topological charges in upward and downward radiation channels. Our approach involves a photonic crystal slab (PCS) that initially exhibits both out-of-plane and in-plane mirror symmetry, and this PCS possesses one BIC at the Γpoint and two BICs off the Γpoint. By introducing certain perturbations that break the out-of-plane mirror symmetry, the two off-ΓBICs decompose into four circularly polarized states (C points) with identical topological charges (each with half the topological charge of the original BIC) while the at-ΓBIC is preserved. Then, we selectively manipulate the four C points associated with the downward radiation channel to converge at the at-ΓBIC, forming a Janus BIC with distinct topological charges for upward and downward radiation. By further introducing in-plane mirror symmetry perturbation, we can bring two of the C points with the same handedness and identical topological charges for upward radiation to merge into the Janus BIC. This process results in a Janus chiral BIC which exhibits large intrinsic chirality and an infinite Q factor. Janus BICs can induce distinct Pancharatnam-Berry phase singularities in momentum space for different incident channels, providing a new approach to control orbital angular momentum. Janus chiral BICs hold promise in enhancing direction-dependent and spin-dependent asymmetric light-matter interaction, opening new pathways for improving chirality-dependent operation for on-chip devices.

physics.optics↗

arXiv2025

Family of third-order topological insulators from Su-Schrieffer-Heeger stacking

We construct a family of chiral symmetry-protected third-order topological insulators by stacking Su-Schrieffer-Heeger (SSH) chains and provide a unified topological characterization by a series of Bott indices. Our approach is informed by the analytical solution of corner states for the model Hamiltonians written as a summation of the extended SSH model along three orthogonal directions. By utilizing the generalized Pauli matrices, an enumeration of the constructed model Hamiltonians generates ten distinct models, including the well-studied three-dimensional Benalcazar-Bernevig-Hughes model. By performing a boundary projection analysis for the ten models, we find that certain surfaces and hinges of the systems can exhibit, respectively, nontrivial second-order and first-order topology in the phase of the third-order topological insulators. Furthermore, we analyze the phase diagram for one of the predicted models and reveal a rich set of topological phases, including the third-order topological insulators, second-order weak topological insulators, and second-order nodal semimetals.

cond-mat.mes-hall↗

arXiv2025

Braiding rule of boundary Majorana-like zero mode

The study of topological states has become an important topic in both solid-state systems and artificial structures such as photonic crystals and phononic crystals. Among them, Majorana zero modes, which exhibit nontrivial braiding process, have attracted extensive research interest. The analog of Majorana zero modes in classical waves, or the Majorana-like zero modes (MLZMs), have also got a lot of attention recently. However, the vast majority of previous works concerned with MLZMs that were bounded to vortexes inside the bulk. Here in this work, we unveil the braiding rule of MLZMs that are tunable around the boundary of a vortex-texture Kekule modulated graphene. We show that the existence of these zero-dimensional boundary MLZMs is protected by the Zak phase of 1D boundary states. As such, we are able to construct multiple MLZMs and analyze the corresponding braiding process. In addition, we also provide an implementation scheme of the boundary MLZMs in acoustic crystals. The tunability of the boundary MLZMs proposed herein offer new freedom for topological states braiding in both solid-state systems and artificial structures.

cond-mat.mes-hall↗

arXiv2024

GeneSUM: Large Language Model-based Gene Summary Extraction

Emerging topics in biomedical research are continuously expanding, providing a wealth of information about genes and their function. This rapid proliferation of knowledge presents unprecedented opportunities for scientific discovery and formidable challenges for researchers striving to keep abreast of the latest advancements. One significant challenge is navigating the vast corpus of literature to extract vital gene-related information, a time-consuming and cumbersome task. To enhance the efficiency of this process, it is crucial to address several key challenges: (1) the overwhelming volume of literature, (2) the complexity of gene functions, and (3) the automated integration and generation. In response, we propose GeneSUM, a two-stage automated gene summary extractor utilizing a large language model (LLM). Our approach retrieves and eliminates redundancy of target gene literature and then fine-tunes the LLM to refine and streamline the summarization process. We conducted extensive experiments to validate the efficacy of our proposed framework. The results demonstrate that LLM significantly enhances the integration of gene-specific information, allowing more efficient decision-making in ongoing research.

q-bio.GN↗

arXiv2024

scReader: Prompting Large Language Models to Interpret scRNA-seq Data

Large language models (LLMs) have demonstrated remarkable advancements, primarily due to their capabilities in modeling the hidden relationships within text sequences. This innovation presents a unique opportunity in the field of life sciences, where vast collections of single-cell omics data from multiple species provide a foundation for training foundational models. However, the challenge lies in the disparity of data scales across different species, hindering the development of a comprehensive model for interpreting genetic data across diverse organisms. In this study, we propose an innovative hybrid approach that integrates the general knowledge capabilities of LLMs with domain-specific representation models for single-cell omics data interpretation. We begin by focusing on genes as the fundamental unit of representation. Gene representations are initialized using functional descriptions, leveraging the strengths of mature language models such as LLaMA-2. By inputting single-cell gene-level expression data with prompts, we effectively model cellular representations based on the differential expression levels of genes across various species and cell types. In the experiments, we constructed developmental cells from humans and mice, specifically targeting cells that are challenging to annotate. We evaluated our methodology through basic tasks such as cell annotation and visualization analysis. The results demonstrate the efficacy of our approach compared to other methods using LLMs, highlighting significant improvements in accuracy and interoperability. Our hybrid approach enhances the representation of single-cell data and offers a robust framework for future research in cross-species genetic analysis.

q-bio.GN↗

arXiv2024

Prospect of measuring the top quark mass through energy correlators

Reaching a high precision of the top quark mass is an important task of the Large Hadron Collider. We perform a feasibility study of measuring the top quark mass through the three-point energy correlator. The expected sensitivity of the top quark mass in the boosted regime is presented. We further introduce its application to the low top $p_\text{T}$ regime and demonstrate that both the W boson and the top quark masses could be extracted from this single observable. Compared to traditional observables, the energy correlator shows robustness to uncertainties that usually dominate experimental measurements and provides a promising way to improve experimental precision.

hep-ph↗

arXiv2024

Semi-supervised Domain Adaptation in Graph Transfer Learning

As a specific case of graph transfer learning, unsupervised domain adaptation on graphs aims for knowledge transfer from label-rich source graphs to unlabeled target graphs. However, graphs with topology and attributes usually have considerable cross-domain disparity and there are numerous real-world scenarios where merely a subset of nodes are labeled in the source graph. This imposes critical challenges on graph transfer learning due to serious domain shifts and label scarcity. To address these challenges, we propose a method named Semi-supervised Graph Domain Adaptation (SGDA). To deal with the domain shift, we add adaptive shift parameters to each of the source nodes, which are trained in an adversarial manner to align the cross-domain distributions of node embedding, thus the node classifier trained on labeled source nodes can be transferred to the target nodes. Moreover, to address the label scarcity, we propose pseudo-labeling on unlabeled nodes, which improves classification on the target graph via measuring the posterior influence of nodes based on their relative position to the class centroids. Finally, extensive experiments on a range of publicly accessible datasets validate the effectiveness of our proposed SGDA in different experimental settings.

cs.LG↗

arXiv2024

Towards Graph Prompt Learning: A Survey and Beyond

Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements and computational costs while enhancing model applicability across various tasks. Graphs, as versatile data structures that capture relationships between entities, play pivotal roles in fields such as social network analysis, recommender systems, and biological graphs. Despite the success of pre-train and prompt learning paradigms in Natural Language Processing (NLP) and Computer Vision (CV), their application in graph domains remains nascent. In graph-structured data, not only do the node and edge features often have disparate distributions, but the topological structures also differ significantly. This diversity in graph data can lead to incompatible patterns or gaps between pre-training and fine-tuning on downstream graphs. We aim to bridge this gap by summarizing methods for alleviating these disparities. This includes exploring prompt design methodologies, comparing related techniques, assessing application scenarios and datasets, and identifying unresolved problems and challenges. This survey categorizes over 100 relevant works in this field, summarizing general design principles and the latest applications, including text-attributed graphs, molecules, proteins, and recommendation systems. Through this extensive review, we provide a foundational understanding of graph prompt learning, aiming to impact not only the graph mining community but also the broader Artificial General Intelligence (AGI) community.

cs.LG↗

arXiv2024

BioRAG: A RAG-LLM Framework for Biological Question Reasoning

The question-answering system for Life science research, which is characterized by the rapid pace of discovery, evolving insights, and complex interactions among knowledge entities, presents unique challenges in maintaining a comprehensive knowledge warehouse and accurate information retrieval. To address these issues, we introduce BioRAG, a novel Retrieval-Augmented Generation (RAG) with the Large Language Models (LLMs) framework. Our approach starts with parsing, indexing, and segmenting an extensive collection of 22 million scientific papers as the basic knowledge, followed by training a specialized embedding model tailored to this domain. Additionally, we enhance the vector retrieval process by incorporating a domain-specific knowledge hierarchy, which aids in modeling the intricate interrelationships among each query and context. For queries requiring the most current information, BioRAG deconstructs the question and employs an iterative retrieval process incorporated with the search engine for step-by-step reasoning. Rigorous experiments have demonstrated that our model outperforms fine-tuned LLM, LLM with search engines, and other scientific RAG frameworks across multiple life science question-answering tasks.

cs.CL↗

arXiv2024

Exceptional features in nonlinear Hermitian systems

Non-Hermitian systems and their topological singularities, such as exceptional points (EPs), lines, and surfaces, have recently attracted intense interest. The investigation of these exceptional constituents has led to fruitful applications. The responsivity of the eigenvalue diverges at EPs, and chiral state transfer occurs when encircling an EP. Traditionally, it was believed that these exceptional features were unique to non-Hermitian systems requiring gain, loss, or nonreciprocal hopping. Here, we show that these exceptional features are also present in nonlinear Hermitian systems. We consider two coupled resonators with Kerr nonlinearity in one resonator, and no non-Hermitian terms. We identify EP-like points (ELPs) on the eigenspectra where the critical behaviors are the same as those of typical EPs. Additionally, this nonlinear Hermitian system can be mapped to linear non-Hermitian systems, with ELPs corresponding to EPs. We also demonstrate that encirclement around an ELP in the parameter space leads to unique chiral state transfer behavior.

physics.optics↗

arXiv2024

Applications of Bound States in the Continuum in Photonics

Bound states in the continuum (BICs) have attracted attention in photonics owing to their interesting properties. For example, BICs can effectively confine light in a counter-intuitive way and the far-field radiation of photonic structures that exhibit BICs manifests fascinating topological characteristics. Early research into photonic BICs was primarily focused on designing artificial structures to produce BICs. However, since the mid-2010s, exploring the potential applications of BICs has been a growing trend in research. In this Review, we detail the unique properties of BICs, including the ability to achieve enhanced light confinement, sharp Fano resonances, and topological characteristics. We also explore phenomena derived from BICs including the generation of circularly polarized states and unidirectional guided resonances and the impact of BICs on various applications such as lasing, nonlinear frequency conversion, waveguiding, sensing and wavefront control. We also discuss the insights provided by BICs in several emerging research frontiers, such as parity-time symmetric systems, higher-order topology, exciton-photon coupling, and moiré superlattices.

physics.optics↗

arXiv2024

GUME: Graphs and User Modalities Enhancement for Long-Tail Multimodal Recommendation

Multimodal recommendation systems (MMRS) have received considerable attention from the research community due to their ability to jointly utilize information from user behavior and product images and text. Previous research has two main issues. First, many long-tail items in recommendation systems have limited interaction data, making it difficult to learn comprehensive and informative representations. However, past MMRS studies have overlooked this issue. Secondly, users' modality preferences are crucial to their behavior. However, previous research has primarily focused on learning item modality representations, while user modality representations have remained relatively simplistic.To address these challenges, we propose a novel Graphs and User Modalities Enhancement (GUME) for long-tail multimodal recommendation. Specifically, we first enhance the user-item graph using multimodal similarity between items. This improves the connectivity of long-tail items and helps them learn high-quality representations through graph propagation. Then, we construct two types of user modalities: explicit interaction features and extended interest features. By using the user modality enhancement strategy to maximize mutual information between these two features, we improve the generalization ability of user modality representations. Additionally, we design an alignment strategy for modality data to remove noise from both internal and external perspectives. Extensive experiments on four publicly available datasets demonstrate the effectiveness of our approach.

cs.IR↗

arXiv2024

Controlling quasi-parametric amplifications: From multiple PT-symmetry phase transitions to non-Hermitian sensing

Quasi-parametric amplification (QPA) is a nonlinear interaction in which the idler wave is depleted through some loss mechanism. QPA plays an important role in signal amplification in ultrafast photonics and quantum light generation. The QPA process has a number of features characterized by the non-Hermitian parity-time ($\mathcal{PT}$) symmetry. In this report, we explore new interaction regimes and uncover multiple $\mathcal{PT}$-symmetry phase transitions in such QPA process where transitions are particularly sensitive to external parameters. In particular, we demonstrate the feasibility of detection of $10^{-11}$ inhomogeneities of the doped absorber, which is order of magnitude more sensitive than similar measurements performed in a linear absorption regime. In doing so, we reveal a family of $\mathcal{PT}$-symmetry phase transitions appearing in the QPA process and provide a novel nonlinear optical sensing mechanism for precise optical measurements.

physics.optics↗

arXiv2024

Photonic realization of chiral hinge states in a Chern-insulator stack

Higher-order topological insulators, as a novel family of topological phases, are a hot frontier in condensed matter physics due to their adherence to unconventional bulk-boundary correspondence. A three-dimensional second-order topological insulator can support one-dimensional modes along its hinges (dubbed as hinge states). Here, we present a simple and direct method to construct chiral hinge modes based on a Chern-insulator stack. We analyze the existence of the hinge modes through the nontrivial quadrupole indices, and then design a photonic crystal to realize the specific flowing pattern of the hinge mode in our model. The experimental results align well with full-wave simulations, clearly demonstrating the existence of chiral hinge states. We also verify the robustness of these hinge states against defects in our photonic system.

cond-mat.mes-hall↗

arXiv2024

Enhancing Tabular Data Optimization with a Flexible Graph-based Reinforced Exploration Strategy

Tabular data optimization methods aim to automatically find an optimal feature transformation process that generates high-value features and improves the performance of downstream machine learning tasks. Current frameworks for automated feature transformation rely on iterative sequence generation tasks, optimizing decision strategies through performance feedback from downstream tasks. However, these approaches fail to effectively utilize historical decision-making experiences and overlook potential relationships among generated features, thus limiting the depth of knowledge extraction. Moreover, the granularity of the decision-making process lacks dynamic backtracking capabilities for individual features, leading to insufficient adaptability when encountering inefficient pathways, adversely affecting overall robustness and exploration efficiency. To address the limitations observed in current automatic feature engineering frameworks, we introduce a novel method that utilizes a feature-state transformation graph to effectively preserve the entire feature transformation journey, where each node represents a specific transformation state. During exploration, three cascading agents iteratively select nodes and idea mathematical operations to generate new transformation states. This strategy leverages the inherent properties of the graph structure, allowing for the preservation and reuse of valuable transformations. It also enables backtracking capabilities through graph pruning techniques, which can rectify inefficient transformation paths. To validate the efficacy and flexibility of our approach, we conducted comprehensive experiments and detailed case studies, demonstrating superior performance in diverse scenarios.

cs.LG↗

arXiv2024

Enhanced Gene Selection in Single-Cell Genomics: Pre-Filtering Synergy and Reinforced Optimization

Recent advancements in single-cell genomics necessitate precision in gene panel selection to interpret complex biological data effectively. Those methods aim to streamline the analysis of scRNA-seq data by focusing on the most informative genes that contribute significantly to the specific analysis task. Traditional selection methods, which often rely on expert domain knowledge, embedded machine learning models, or heuristic-based iterative optimization, are prone to biases and inefficiencies that may obscure critical genomic signals. Recognizing the limitations of traditional methods, we aim to transcend these constraints with a refined strategy. In this study, we introduce an iterative gene panel selection strategy that is applicable to clustering tasks in single-cell genomics. Our method uniquely integrates results from other gene selection algorithms, providing valuable preliminary boundaries or prior knowledge as initial guides in the search space to enhance the efficiency of our framework. Furthermore, we incorporate the stochastic nature of the exploration process in reinforcement learning (RL) and its capability for continuous optimization through reward-based feedback. This combination mitigates the biases inherent in the initial boundaries and harnesses RL's adaptability to refine and target gene panel selection dynamically. To illustrate the effectiveness of our method, we conducted detailed comparative experiments, case studies, and visualization analysis.

cs.AI↗

arXiv2024

Distribution-Aware Data Expansion with Diffusion Models

The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion technologies aim to automatically augment datasets, unlocking the full potential of deep models. Current data expansion techniques include image transformation and image synthesis methods. Transformation-based methods introduce only local variations, leading to limited diversity. In contrast, synthesis-based methods generate entirely new content, greatly enhancing informativeness. However, existing synthesis methods carry the risk of distribution deviations, potentially degrading model performance with out-of-distribution samples. In this paper, we propose DistDiff, a training-free data expansion framework based on the distribution-aware diffusion model. DistDiff constructs hierarchical prototypes to approximate the real data distribution, optimizing latent data points within diffusion models with hierarchical energy guidance. We demonstrate its capability to generate distribution-consistent samples, significantly improving data expansion tasks. DistDiff consistently enhances accuracy across a diverse range of datasets compared to models trained solely on original data. Furthermore, our approach consistently outperforms existing synthesis-based techniques and demonstrates compatibility with widely adopted transformation-based augmentation methods. Additionally, the expanded dataset exhibits robustness across various architectural frameworks. Our code is available at https://github.com/haoweiz23/DistDiff

cs.CV↗