arXiv subjects

Xiaoze Liu

Publications and source records attributed to Xiaoze Liu.

33 records · Page 2Linked to original sources

arXiv2024

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for innovation. In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm. We begin by defining KGs and MMKGs, then explore their construction progress. Our review includes two primary task categories: KG-aware multi-modal learning tasks, such as Image Classification and Visual Question Answering, and intrinsic MMKG tasks like Multi-modal Knowledge Graph Completion and Entity Alignment, highlighting specific research trajectories. For most of these tasks, we provide definitions, evaluation benchmarks, and additionally outline essential insights for conducting relevant research. Finally, we discuss current challenges and identify emerging trends, such as progress in Large Language Modeling and Multi-modal Pre-training strategies. This survey aims to serve as a comprehensive reference for researchers already involved in or considering delving into KG and multi-modal learning research, offering insights into the evolving landscape of MMKG research and supporting future work.

cs.AI↗

arXiv2023

Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity

This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital. We define the Factuality Issue as the probability of LLMs to produce content inconsistent with established facts. We first delve into the implications of these inaccuracies, highlighting the potential consequences and challenges posed by factual errors in LLM outputs. Subsequently, we analyze the mechanisms through which LLMs store and process facts, seeking the primary causes of factual errors. Our discussion then transitions to methodologies for evaluating LLM factuality, emphasizing key metrics, benchmarks, and studies. We further explore strategies for enhancing LLM factuality, including approaches tailored for specific domains. We focus two primary LLM configurations standalone LLMs and Retrieval-Augmented LLMs that utilizes external data, we detail their unique challenges and potential enhancements. Our survey offers a structured guide for researchers aiming to fortify the factual reliability of LLMs.

cs.CL↗

arXiv2023

Universal Multi-modal Entity Alignment via Iteratively Fusing Modality Similarity Paths

The objective of Entity Alignment (EA) is to identify equivalent entity pairs from multiple Knowledge Graphs (KGs) and create a more comprehensive and unified KG. The majority of EA methods have primarily focused on the structural modality of KGs, lacking exploration of multi-modal information. A few multi-modal EA methods have made good attempts in this field. Still, they have two shortcomings: (1) inconsistent and inefficient modality modeling that designs complex and distinct models for each modality; (2) ineffective modality fusion due to the heterogeneous nature of modalities in EA. To tackle these challenges, we propose PathFusion, consisting of two main components: (1) MSP, a unified modeling approach that simplifies the alignment process by constructing paths connecting entities and modality nodes to represent multiple modalities; (2) IRF, an iterative fusion method that effectively combines information from different modalities using the path as an information carrier. Experimental results on real-world datasets demonstrate the superiority of PathFusion over state-of-the-art methods, with 22.4%-28.9% absolute improvement on Hits@1, and 0.194-0.245 absolute improvement on MRR.

cs.CL↗

arXiv2023

MultiEM: Efficient and Effective Unsupervised Multi-Table Entity Matching

Entity Matching (EM), which aims to identify all entity pairs referring to the same real-world entity from relational tables, is one of the most important tasks in real-world data management systems. Due to the labeling process of EM being extremely labor-intensive, unsupervised EM is more applicable than supervised EM in practical scenarios. Traditional unsupervised EM assumes that all entities come from two tables; however, it is more common to match entities from multiple tables in practical applications, that is, multi-table entity matching (multi-table EM). Unfortunately, effective and efficient unsupervised multi-table EM remains under-explored. To fill this gap, this paper formally studies the problem of unsupervised multi-table entity matching and proposes an effective and efficient solution, termed as MultiEM. MultiEM is a parallelable pipeline of enhanced entity representation, table-wise hierarchical merging, and density-based pruning. Extensive experimental results on six real-world benchmark datasets demonstrate the superiority of MultiEM in terms of effectiveness and efficiency.

cs.DB↗

arXiv2023

Real-time Workload Pattern Analysis for Large-scale Cloud Databases

Hosting database services on cloud systems has become a common practice. This has led to the increasing volume of database workloads, which provides the opportunity for pattern analysis. Discovering workload patterns from a business logic perspective is conducive to better understanding the trends and characteristics of the database system. However, existing workload pattern discovery systems are not suitable for large-scale cloud databases which are commonly employed by the industry. This is because the workload patterns of large-scale cloud databases are generally far more complicated than those of ordinary databases. In this paper, we propose Alibaba Workload Miner (AWM), a real-time system for discovering workload patterns in complicated large-scale workloads. AWM encodes and discovers the SQL query patterns logged from user requests and optimizes the querying processing based on the discovered patterns. First, Data Collection & Preprocessing Module collects streaming query logs and encodes them into high-dimensional feature embeddings with rich semantic contexts and execution features. Next, Online Workload Mining Module separates encoded queries by business groups and discovers the workload patterns for each group. Meanwhile, Offline Training Module collects labels and trains the classification model using the labels. Finally, Pattern-based Optimizing Module optimizes query processing in cloud databases by exploiting discovered patterns. Extensive experimental results on one synthetic dataset and two real-life datasets (extracted from Alibaba Cloud databases) show that AWM enhances the accuracy of pattern discovery by 66% and reduce the latency of online inference by 22%, compared with the state-of-the-arts.

cs.DB↗

arXiv2023

Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness

Systems for serving inference requests on graph neural networks (GNN) must combine low latency with high throughout, but they face irregular computation due to skew in the number of sampled graph nodes and aggregated GNN features. This makes it challenging to exploit GPUs effectively: using GPUs to sample only a few graph nodes yields lower performance than CPU-based sampling; and aggregating many features exhibits high data movement costs between GPUs and CPUs. Therefore, current GNN serving systems use CPUs for graph sampling and feature aggregation, limiting throughput. We describe Quiver, a distributed GPU-based GNN serving system with low-latency and high-throughput. Quiver's key idea is to exploit workload metrics for predicting the irregular computation of GNN requests, and governing the use of GPUs for graph sampling and feature aggregation: (1) for graph sampling, Quiver calculates the probabilistic sampled graph size, a metric that predicts the degree of parallelism in graph sampling. Quiver uses this metric to assign sampling tasks to GPUs only when the performance gains surpass CPU-based sampling; and (2) for feature aggregation, Quiver relies on the feature access probability to decide which features to partition and replicate across a distributed GPU NUMA topology. We show that Quiver achieves up to 35 times lower latency with an 8 times higher throughput compared to state-of-the-art GNN approaches (DGL and PyG).

cs.DC↗

arXiv2023

Unsupervised Entity Alignment for Temporal Knowledge Graphs

Entity alignment (EA) is a fundamental data integration task that identifies equivalent entities between different knowledge graphs (KGs). Temporal Knowledge graphs (TKGs) extend traditional knowledge graphs by introducing timestamps, which have received increasing attention. State-of-the-art time-aware EA studies have suggested that the temporal information of TKGs facilitates the performance of EA. However, existing studies have not thoroughly exploited the advantages of temporal information in TKGs. Also, they perform EA by pre-aligning entity pairs, which can be labor-intensive and thus inefficient. In this paper, we present DualMatch which effectively fuses the relational and temporal information for EA. DualMatch transfers EA on TKGs into a weighted graph matching problem. More specifically, DualMatch is equipped with an unsupervised method, which achieves EA without necessitating seed alignment. DualMatch has two steps: (i) encoding temporal and relational information into embeddings separately using a novel label-free encoder, Dual-Encoder; and (ii) fusing both information and transforming it into alignment using a novel graph-matching-based decoder, GM-Decoder. DualMatch is able to perform EA on TKGs with or without supervision, due to its capability of effectively capturing temporal information. Extensive experiments on three real-world TKG datasets offer the insight that DualMatch outperforms the state-of-the-art methods in terms of H@1 by 2.4% - 10.7% and MRR by 1.7% - 7.6%, respectively.

cs.IR↗

arXiv2023

Self-Induced Valley Bosonic Stimulation of Exciton-Polaritons in a Monolayer Semiconductor

The newly discovered valley degree of freedom in atomically thin two-dimensional transition metal dichalcogenides (TMD) offers a promising platform to explore rich nonlinear physics, such as spinor Bose-Einstein condensate (BEC) and novel valleytronics applications. However, the critical nonlinear effect, such as valley polariton bosonic stimulation, has long remained an unresolved challenge due to the generation of limited polariton ground state densities necessary to induce the stimulated scattering of polaritons in specific valleys. Here, we report the self-induced valley bosonic stimulation of exciton-polaritons via spin-valley locking in a WS2 monolayer microcavity. This is achieved by the resonant injection of valley polaritons at specific energy and wavevector, which allows spin-polarized polaritons to efficiently populate their ground state and induce a valley-dependent bosonic stimulation. As a result, we observe the nonlinear self-amplification of polariton emission from the valley-dependent ground state. Our finding paves the way for the investigation of spin ordering and phase transitions in TMD polariton BEC, offering a promising route for the realization of polariton spin lattices in moiré polariton systems and spin-lasers.

cond-mat.mes-hall↗

arXiv2022

ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities

Entity alignment (EA) aims at finding equivalent entities in different knowledge graphs (KGs). Embedding-based approaches have dominated the EA task in recent years. Those methods face problems that come from the geometric properties of embedding vectors, including hubness and isolation. To solve these geometric problems, many normalization approaches have been adopted for EA. However, the increasing scale of KGs renders it hard for EA models to adopt the normalization processes, thus limiting their usage in real-world applications. To tackle this challenge, we present ClusterEA, a general framework that is capable of scaling up EA models and enhancing their results by leveraging normalization methods on mini-batches with a high entity equivalent rate. ClusterEA contains three components to align entities between large-scale KGs, including stochastic training, ClusterSampler, and SparseFusion. It first trains a large-scale Siamese GNN for EA in a stochastic fashion to produce entity embeddings. Based on the embeddings, a novel ClusterSampler strategy is proposed for sampling highly overlapped mini-batches. Finally, ClusterEA incorporates SparseFusion, which normalizes local and global similarity and then fuses all similarity matrices to obtain the final similarity matrix. Extensive experiments with real-life datasets on EA benchmarks offer insight into the proposed framework, and suggest that it is capable of outperforming the state-of-the-art scalable EA framework by up to 8 times in terms of Hits@1.

cs.DB↗

arXiv2022

Electrically pumped polarized exciton-polaritons in a halide perovskite microcavity

Exciton polaritons, hybrid quasiparticles with part-light part-matter nature in semiconductor microcavities, are extensively investigated for striking phenomena such as polariton condensation and quantum emulation. These phenomena have recently been discovered in emerging lead halide perovskites at elevated temperatures up to room temperature. For advancing these discoveries into practical applications, one critical requirement is the realization of electrically pumped exciton-polaritons. However, electrically pumped polariton light-emitting devices with perovskites have not yet been achieved experimentally. Here, we devise a new method to combine the device with the microcavity and report the first halide perovskite polariton light-emitting device. Specifically, the device is based on a CsPbBr3 capacitive structure, which can inject the electrons and holes from the same electrode, conducive to the formation of excitons and simultaneously maintaining the high quality of the microcavity. In addition, highly polarization-selective polariton emissions have been demonstrated due to the optical birefringence in the CsPbBr3 microplate. This work paves the way for realizing practical polaritonic devices such as high-speed light-emitting devices for information communications and inversionless electrically pumped lasers based on perovskites.

cond-mat.mtrl-sci↗

arXiv2021

LargeEA: Aligning Entities for Large-scale Knowledge Graphs

Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). Current EA approaches suffer from scalability issues, limiting their usage in real-world EA scenarios. To tackle this challenge, we propose LargeEA to align entities between large-scale KGs. LargeEA consists of two channels, i.e., structure channel and name channel. For the structure channel, we present METIS-CPS, a memory-saving mini-batch generation strategy, to partition large KGs into smaller mini-batches. LargeEA, designed as a general tool, can adopt any existing EA approach to learn entities' structural features within each mini-batch independently. For the name channel, we first introduce NFF, a name feature fusion method, to capture rich name features of entities without involving any complex training process. Then, we exploit a name-based data augmentation to generate seed alignment without any human intervention. Such design fits common real-world scenarios much better, as seed alignment is not always available. Finally, LargeEA derives the EA results by fusing the structural features and name features of entities. Since no widely-acknowledged benchmark is available for large-scale EA evaluation, we also develop a large-scale EA benchmark called DBP1M extracted from real-world KGs. Extensive experiments confirm the superiority of LargeEA against state-of-the-art competitors.

cs.DB↗

arXiv2021

CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration

Entity Resolution (ER) aims to identify whether two tuples refer to the same real-world entity and is well-known to be labor-intensive. It is a prerequisite to anomaly detection, as comparing the attribute values of two matched tuples from two different datasets provides one effective way to detect anomalies. Existing ER approaches, due to insufficient feature discovery or error-prone inherent characteristics, are not able to achieve stable performance. In this paper, we present CollaborER, a self-supervised entity resolution framework via multi-features collaboration. It is capable of (i) obtaining reliable ER results with zero human annotations and (ii) discovering adequate tuples' features in a fault-tolerant manner. CollaborER consists of two phases, i.e., automatic label generation (ALG) and collaborative ER training (CERT). In the first phase, ALG is proposed to generate a set of positive tuple pairs and a set of negative tuple pairs. ALG guarantees the high quality of the generated tuples and hence ensures the training quality of the subsequent CERT. In the second phase, CERT is introduced to learn the matching signals by discovering graph features and sentence features of tuples collaboratively. Extensive experimental results over eight real-world ER benchmarks show that CollaborER outperforms all the existing unsupervised ER approaches and is comparable or even superior to the state-of-the-art supervised ER methods.

cs.DB↗

arXiv2020

Engineering photonic environments for two-dimensional materials

A fascinating photonic platform with a small device scale, fast operating speed, as well as low energy consumption is two-dimensional (2D) materials, thanks to their in-plane crystalline structures and out-of-plane quantum confinement. The key to further advancement in this research field is the ability to modify the optical properties of the 2D materials. The modifications typically come from the materials themselves, for example, altering their chemical compositions. This article reviews a comparably less explored but promising means, through engineering the photonic surroundings. Rather than modifying materials themselves, this means manipulates the dielectric and metallic environments, both uniform and nanostructured, that directly interact with the materials. For 2D materials that are only one or a few atoms thick, the interaction with the environment can be remarkably efficient. This review summarizes the three degrees of freedom of this interaction: weak coupling, strong coupling, and multi-functionality. Also, it reviews a relatively timing concept of engineering that directly applied to the 2D materials by patterning. Benefiting from the burgeoning development of nanophotonics, the engineering of photonic environments provides a versatile and creative methodology of reshaping light-matter interaction in 2D materials.

physics.optics↗

arXiv2019

Observation of Rydberg exciton polaritons and their condensate in a perovskite cavity

The condensation of half-light half-matter exciton polaritons in semiconductor optical cavities is a striking example of macroscopic quantum coherence in a solid state platform. Quantum coherence is possible only when there are strong interactions between the exciton polaritons provided by their excitonic constituents. Rydberg excitons with high principle value exhibit strong dipole-dipole interactions in cold atoms. However, polaritons with the excitonic constituent that is an excited state, namely Rydberg exciton polaritons (REPs), have not yet been experimentally observed. Here, for the first time, we observe the formation of REPs in a single crystal CsPbBr3 perovskite cavity without any external fields. These polaritons exhibit strong nonlinear behavior that leads to a coherent polariton condensate with a prominent blue shift. Furthermore, the REPs in CsPbBr3 are highly anisotropic and have a large extinction ratio, arising from the perovskite's orthorhombic crystal structure. Our observation not only sheds light on the importance of many-body physics in coherent polariton systems involving higher-order excited states, but also paves the way for exploring these coherent interactions for solid state quantum optical information processing.

cond-mat.mtrl-sci↗

arXiv2014

Strong light-matter coupling in two-dimensional atomic crystals

Two dimensional (2D) atomic crystals of graphene, and transition metal dichalcogenides have emerged as a class of materials that show strong light-matter interaction. This interaction can be further controlled by embedding such materials into optical microcavities. When the interaction is engineered to be stronger than the dissipation of light and matter entities, one approaches the strong coupling regime resulting in the formation of half-light half-matter bosonic quasiparticles called microcavity polaritons. Here we report the evidence of strong light-matter coupling and formation of microcavity polaritons in a two dimensional atomic crystal of molybdenum disulphide (MoS2) embedded inside a dielectric microcavity at room temperature. A Rabi splitting of 46 meV and highly directional emission is observed from the MoS2 microcavity owing to the coupling between the 2D excitons and the cavity photons. Realizing strong coupling effects at room temperature in a disorder free potential landscape is central to the development of practical polaritonic circuits and switches.

physics.optics↗