arXiv subjects

Xin Mao

Publications and source records attributed to Xin Mao.

35 records · Page 2Linked to original sources

arXiv2024

HiLight: Technical Report on the Motern AI Video Language Model

This technical report presents the implementation of a state-of-the-art video encoder for video-text modal alignment and a video conversation framework called HiLight, which features dual visual towers. The work is divided into two main parts: 1.alignment of video and text modalities; 2.convenient and efficient way to interact with users. Our goal is to address the task of video comprehension in the context of billiards. The report includes a discussion of the concepts and the final solution developed during the task's implementation.

cs.CV↗

arXiv2024

Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space

Temporal knowledge graph completion (TKGC) aims to fill in missing facts within a given temporal knowledge graph at a specific time. Existing methods, operating in real or complex spaces, have demonstrated promising performance in this task. This paper advances beyond conventional approaches by introducing more expressive quaternion representations for TKGC within hypercomplex space. Unlike existing quaternion-based methods, our study focuses on capturing time-sensitive relations rather than time-aware entities. Specifically, we model time-sensitive relations through time-aware rotation and periodic time translation, effectively capturing complex temporal variability. Furthermore, we theoretically demonstrate our method's capability to model symmetric, asymmetric, inverse, compositional, and evolutionary relation patterns. Comprehensive experiments on public datasets validate that our proposed approach achieves state-of-the-art performance in the field of TKGC.

cs.LG↗

arXiv2024

A Survey on Temporal Knowledge Graph: Representation Learning and Applications

Knowledge graphs have garnered significant research attention and are widely used to enhance downstream applications. However, most current studies mainly focus on static knowledge graphs, whose facts do not change with time, and disregard their dynamic evolution over time. As a result, temporal knowledge graphs have attracted more attention because a large amount of structured knowledge exists only within a specific period. Knowledge graph representation learning aims to learn low-dimensional vector embeddings for entities and relations in a knowledge graph. The representation learning of temporal knowledge graphs incorporates time information into the standard knowledge graph framework and can model the dynamics of entities and relations over time. In this paper, we conduct a comprehensive survey of temporal knowledge graph representation learning and its applications. We begin with an introduction to the definitions, datasets, and evaluation metrics for temporal knowledge graph representation learning. Next, we propose a taxonomy based on the core technologies of temporal knowledge graph representation learning methods, and provide an in-depth analysis of different methods in each category. Finally, we present various downstream applications related to the temporal knowledge graphs. In the end, we conclude the paper and have an outlook on the future research directions in this area.

cs.CL↗

arXiv2024

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration

While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal Policy Optimization (PPO) algorithm, proposing a series of order-based calibration methods as viable alternatives. This paper delves further into current order-based methods, examining their inefficiencies in utilizing reward values and addressing misalignment issues. Building upon these findings, we propose a novel \textbf{V}alue-based \textbf{C}ali\textbf{B}ration (VCB) method to better align LLMs with human preferences. Experimental results demonstrate that VCB surpasses existing alignment methods on AI assistant and summarization datasets, providing impressive generalizability, robustness, and stability in diverse settings.

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

An Effective and Efficient Time-aware Entity Alignment Framework via Two-aspect Three-view Label Propagation

Entity alignment (EA) aims to find the equivalent entity pairs between different knowledge graphs (KGs), which is crucial to promote knowledge fusion. With the wide use of temporal knowledge graphs (TKGs), time-aware EA (TEA) methods appear to enhance EA. Existing TEA models are based on Graph Neural Networks (GNN) and achieve state-of-the-art (SOTA) performance, but it is difficult to transfer them to large-scale TKGs due to the scalability issue of GNN. In this paper, we propose an effective and efficient non-neural EA framework between TKGs, namely LightTEA, which consists of four essential components: (1) Two-aspect Three-view Label Propagation, (2) Sparse Similarity with Temporal Constraints, (3) Sinkhorn Operator, and (4) Temporal Iterative Learning. All of these modules work together to improve the performance of EA while reducing the time consumption of the model. Extensive experiments on public datasets indicate that our proposed model significantly outperforms the SOTA methods for EA between TKGs, and the time consumed by LightTEA is only dozens of seconds at most, no more than 10% of the most efficient TEA method.

cs.AI↗

arXiv2023

Muon radiography experiments on the subway overburden structure detection

Muon radiography is an innovative and non-destructive technique for internal density structure imaging, based on measuring the attenuation of cosmic-ray muons after they penetrate the target. Due to the strong penetration ability of muons, the detection range of muon radiography can reach the order of hundreds of meters or even kilometers. Using a portable muon detector composed of plastic scintillators and silicon photomultipliers, we performed a short-duration(1h) flux scanning experiment of the overburden above the platform and tunnel of the Xiaoying West Road subway station under construction. With the observation direction facing up, the detector is placed on the north side of the track and moved eastward from the platform section inside the station to the tunnel section. The scanning length is 264m and a total of 21 locations are observed. By comparing the observed and predicted values of the muon survival ratio at different locations, the experiment accurately detects the jump in thickness at the interface of the platform section and tunnel section. Furthermore, unknown anomalies caused by random placed light brick piles and side passage mouth above the observation locations are detected and confirmed later. This experiment verifies the feasibility of using natural muons to quickly detect abnormal structures of the overburden of tunnel, and shows that muon radiography has broad application prospects in tunnel safety and other similar aspects.

physics.ins-det↗

arXiv2022

LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation

Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs. In this paper, we argue that existing GNN-based EA methods inherit the inborn defects from their neural network lineage: weak scalability and poor interpretability. Inspired by recent studies, we reinvent the Label Propagation algorithm to effectively run on KGs and propose a non-neural EA framework -- LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Iteration. According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many.

cs.AI↗

arXiv2022

A Simple Temporal Information Matching Mechanism for Entity Alignment Between Temporal Knowledge Graphs

Entity alignment (EA) aims to find entities in different knowledge graphs (KGs) that refer to the same object in the real world. Recent studies incorporate temporal information to augment the representations of KGs. The existing methods for EA between temporal KGs (TKGs) utilize a time-aware attention mechanism to incorporate relational and temporal information into entity embeddings. The approaches outperform the previous methods by using temporal information. However, we believe that it is not necessary to learn the embeddings of temporal information in KGs since most TKGs have uniform temporal representations. Therefore, we propose a simple graph neural network (GNN) model combined with a temporal information matching mechanism, which achieves better performance with less time and fewer parameters. Furthermore, since alignment seeds are difficult to label in real-world applications, we also propose a method to generate unsupervised alignment seeds via the temporal information of TKG. Extensive experiments on public datasets indicate that our supervised method significantly outperforms the previous methods and the unsupervised one has competitive performance.

cs.AI↗

arXiv2022

On the Phases of a Semi-Sectorial Matrix

In this paper, we extend the definition of phases of sectorial matrices to those of semi-sectorial matrices, which are possibly singular. Properties of the phases are also extended, including those of the Moore-Penrose generalized inverse, compressions and Schur complements, matrix sums and products. In particular, a majorization relation is established between the phases of the nonzero eigenvalues of $AB$ and the phases of the compressions of $A$ and $B$, which leads to a generalized matrix small phase theorem. For the matrices which are not necessarily semi-sectorial, we define their (largest and smallest) essential phases via diagonal similarity transformation. An explicit expression for the essential phases of a Laplacian matrix of a directed graph is obtained.

math.RA↗

arXiv2021

From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. Meanwhile, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNNbased methods, we successfully transform the cross-lingual EA problem into the assignment problem. Based on this finding, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments show that our proposed unsupervised method even beats advanced supervised methods across all public datasets and has high efficiency, interpretability, and stability.

cs.CL↗

arXiv2021

Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness

Entity alignment (EA) aims to find the equivalent entities in different KGs, which is a crucial step in integrating multiple KGs. However, most existing EA methods have poor scalability and are unable to cope with large-scale datasets. We summarize three issues leading to such high time-space complexity in existing EA methods: (1) Inefficient graph encoders, (2) Dilemma of negative sampling, and (3) "Catastrophic forgetting" in semi-supervised learning. To address these challenges, we propose a novel EA method with three new components to enable high Performance, high Scalability, and high Robustness (PSR): (1) Simplified graph encoder with relational graph sampling, (2) Symmetric negative-free alignment loss, and (3) Incremental semi-supervised learning. Furthermore, we conduct detailed experiments on several public datasets to examine the effectiveness and efficiency of our proposed method. The experimental results show that PSR not only surpasses the previous SOTA in performance but also has impressive scalability and robustness.

cs.AI↗

arXiv2021

Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining

Seeking the equivalent entities among multi-source Knowledge Graphs (KGs) is the pivotal step to KGs integration, also known as \emph{entity alignment} (EA). However, most existing EA methods are inefficient and poor in scalability. A recent summary points out that some of them even require several days to deal with a dataset containing 200,000 nodes (DWY100K). We believe over-complex graph encoder and inefficient negative sampling strategy are the two main reasons. In this paper, we propose a novel KG encoder -- Dual Attention Matching Network (Dual-AMN), which not only models both intra-graph and cross-graph information smartly, but also greatly reduces computational complexity. Furthermore, we propose the Normalized Hard Sample Mining Loss to smoothly select hard negative samples with reduced loss shift. The experimental results on widely used public datasets indicate that our method achieves both high accuracy and high efficiency. On DWY100K, the whole running process of our method could be finished in 1,100 seconds, at least 10* faster than previous work. The performances of our method also outperform previous works across all datasets, where Hits@1 and MRR have been improved from 6% to 13%.

cs.AI↗

arXiv2020

Relational Reflection Entity Alignment

Entity alignment aims to identify equivalent entity pairs from different Knowledge Graphs (KGs), which is essential in integrating multi-source KGs. Recently, with the introduction of GNNs into entity alignment, the architectures of recent models have become more and more complicated. We even find two counter-intuitive phenomena within these methods: (1) The standard linear transformation in GNNs is not working well. (2) Many advanced KG embedding models designed for link prediction task perform poorly in entity alignment. In this paper, we abstract existing entity alignment methods into a unified framework, Shape-Builder & Alignment, which not only successfully explains the above phenomena but also derives two key criteria for an ideal transformation operation. Furthermore, we propose a novel GNNs-based method, Relational Reflection Entity Alignment (RREA). RREA leverages Relational Reflection Transformation to obtain relation specific embeddings for each entity in a more efficient way. The experimental results on real-world datasets show that our model significantly outperforms the state-of-the-art methods, exceeding by 5.8%-10.9% on Hits@1.

cs.IR↗

arXiv2020

JULOC: A Local 3-D Refined Crust Model for the Geoneutrino Measurement at JUNO

Geothermal energy is the key to drive the plate tectonics and interior thermodynamics of the Earth. The surface heat flux, as measured in boreholes, provide limited insights into the relative contributions of primordial versus radiogenic sources of the heat budget of the mantle. Geoneutrinos, electron antineutrinos that produced from the radioactive decay of the heat producing elements, are unique probes that bring direct information about the amount and distribution of heat producing elements in the crust and mantle. Cosmochemical, geochemical, and geodynamic compositional models of the Bulk Silicate Earth (BSE) individually predicts different mantle neutrino fluxes, and therefore can be distinguished by the direct measurement of geoneutrinos. The 20 kton detector of the Jiangmen Underground Neutrino Observatory (JUNO), currently under construction in the Guangdong Province (China), is expected to provide an exciting opportunity to obtain a high statistics measurement, which will produce sufficient data to address several key questions of geological importance. To test different compositional models of the mantle, an accurate estimation of the crust geoneutrino flux based on a three-dimensional (3-D) crust model in advance is important. This paper presents a 3-D crust model over a surface area of 10-degrees-times-10-degrees grid surrounding the JUNO detector and a depth down to the Moho discontinuity, based on the geological, geophysical and geochemistry properties. The 3-D model provides a distinction of the volumes of the different geological layers together with the corresponding Th and U abundances. We also present our predicted local contribution to the total geoneutrino flux and the corresponding radiogenic heat.

physics.geo-ph↗

arXiv2020

Is Discriminator a Good Feature Extractor?

The discriminator from generative adversarial nets (GAN) has been used by researchers as a feature extractor in transfer learning and appeared worked well. However, there are also studies that believe this is the wrong research direction because intuitively the task of the discriminator focuses on separating the real samples from the generated ones, making features extracted in this way useless for most of the downstream tasks. To avoid this dilemma, we first conducted a thorough theoretical analysis of the relationship between the discriminator task and the features extracted. We found that the connection between the task of the discriminator and the feature is not as strong as was thought, for that the main factor restricting the feature learned by the discriminator is not the task, but is the need to prevent the entire GAN model from mode collapse during the training. From this perspective and combined with further analyses, we found that to avoid mode collapse, the features extracted by the discriminator are not guided to be different for the real samples, but divergence without noise is indeed allowed and occupies a large proportion of the feature space. This makes the features more robust and helps answer the question as to why the discriminator can succeed as a feature extractor in related research. Consequently, to expose the essence of the discriminator extractor as different from other extractors, we analyze the counterpart of the discriminator extractor, the classifier extractor that assigns the target samples to different categories. We found the performance of the discriminator extractor may be inferior to the classifier based extractor when the source classification task is similar to the target task, which is the common case, but the ability to avoid noise prevents the discriminator from being replaced by the classifier.

cs.LG↗

arXiv2019

Non-negligible Oscillation Effects in the Crustal Geo-neutrino Calculations

An accurate prediction of the geo-neutrino signal from the crust serves as a necessary prerequisite in the determination of the geo-neutrino flux from the mantle. In this work we report the non-negligible effect associated to the exact three-flavor antineutrino survival probability in the calculation of the crustal geo-neutrino signal, which was usually approximated as a constant average in previous studies. A geo-neutrino signal underestimation of about 1-2 TNU is observed as a result of the oscillatory behaviour within the local crustal region extending for about 300 km from the experimental site. We also estimated that the Mikheyev-Smirnov-Wolfenstein matter oscillation is responsible for a $0.1\%$-$0.3\%$ increase of the local crustal signal, depending on the detector location. This work reminds that the exact oscillation possibility in matter should be considered for future prediction of the local crustal geo-neutrino signal.

physics.geo-ph↗