arXiv subjects

Lu Chen

Publications and source records attributed to Lu Chen.

At least 253 records · Page 14Linked to original sources

arXiv2023

Finding Materialized Models for Model Reuse

Materialized model query aims to find the most appropriate materialized model as the initial model for model reuse. It is the precondition of model reuse, and has recently attracted much attention. {Nonetheless, the existing methods suffer from the need to provide source data, limited range of applications, and inefficiency since they do not construct a suitable metric to measure the target-related knowledge of materialized models. To address this, we present \textsf{MMQ}, a source-data free, general, efficient, and effective materialized model query framework.} It uses a Gaussian mixture-based metric called separation degree to rank materialized models. For each materialized model, \textsf{MMQ} first vectorizes the samples in the target dataset into probability vectors by directly applying this model, then utilizes Gaussian distribution to fit for each class of probability vectors, and finally uses separation degree on the Gaussian distributions to measure the target-related knowledge of the materialized model. Moreover, we propose an improved \textsf{MMQ} (\textsf{I-MMQ}), which significantly reduces the query time while retaining the query performance of \textsf{MMQ}. Extensive experiments on a range of practical model reuse workloads demonstrate the effectiveness and efficiency of \textsf{MMQ}.

cs.LG↗

arXiv2023

CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset

The cross-domain text-to-SQL task aims to build a system that can parse user questions into SQL on complete unseen databases, and the single-domain text-to-SQL task evaluates the performance on identical databases. Both of these setups confront unavoidable difficulties in real-world applications. To this end, we introduce the cross-schema text-to-SQL task, where the databases of evaluation data are different from that in the training data but come from the same domain. Furthermore, we present CSS, a large-scale CrosS-Schema Chinese text-to-SQL dataset, to carry on corresponding studies. CSS originally consisted of 4,340 question/SQL pairs across 2 databases. In order to generalize models to different medical systems, we extend CSS and create 19 new databases along with 29,280 corresponding dataset examples. Moreover, CSS is also a large corpus for single-domain Chinese text-to-SQL studies. We present the data collection approach and a series of analyses of the data statistics. To show the potential and usefulness of CSS, benchmarking baselines have been conducted and reported. Our dataset is publicly available at \url{https://huggingface.co/datasets/zhanghanchong/css}.

cs.CL↗

arXiv2023

Breaking electron pairs in the pseudogap regime of SmTiO$_3$/SrTiO$_3$/SmTiO$_3$ quantum wells

The strongly correlated two-dimensional electron liquid within SmTiO$_3$/SrTiO$_3$/SmTiO$_3$ quantum well structures exhibits a pseudogap phase when the quantum well width is sufficiently narrow. Using low-temperature transport and optical experiments that drive the quantum-well system out of equilibrium, we find evidence of mobile, long-lived, negatively-charged quasiparticles, consistent with the idea that the pseudogap phase arises from strongly bound electron pairs.

cond-mat.str-el↗

arXiv2023

Knowledge-refined Denoising Network for Robust Recommendation

Knowledge graph (KG), which contains rich side information, becomes an essential part to boost the recommendation performance and improve its explainability. However, existing knowledge-aware recommendation methods directly perform information propagation on KG and user-item bipartite graph, ignoring the impacts of \textit{task-irrelevant knowledge propagation} and \textit{vulnerability to interaction noise}, which limits their performance. To solve these issues, we propose a robust knowledge-aware recommendation framework, called \textit{Knowledge-refined Denoising Network} (KRDN), to prune the task-irrelevant knowledge associations and noisy implicit feedback simultaneously. KRDN consists of an adaptive knowledge refining strategy and a contrastive denoising mechanism, which are able to automatically distill high-quality KG triplets for aggregation and prune noisy implicit feedback respectively. Besides, we also design the self-adapted loss function and the gradient estimator for model optimization. The experimental results on three benchmark datasets demonstrate the effectiveness and robustness of KRDN over the state-of-the-art knowledge-aware methods like KGIN, MCCLK, and KGCL, and also outperform robust recommendation models like SGL and SimGCL.

cs.IR↗

arXiv2023

Towards Explainable Collaborative Filtering with Taste Clusters Learning

Collaborative Filtering (CF) is a widely used and effective technique for recommender systems. In recent decades, there have been significant advancements in latent embedding-based CF methods for improved accuracy, such as matrix factorization, neural collaborative filtering, and LightGCN. However, the explainability of these models has not been fully explored. Adding explainability to recommendation models can not only increase trust in the decisionmaking process, but also have multiple benefits such as providing persuasive explanations for item recommendations, creating explicit profiles for users and items, and assisting item producers in design improvements. In this paper, we propose a neat and effective Explainable Collaborative Filtering (ECF) model that leverages interpretable cluster learning to achieve the two most demanding objectives: (1) Precise - the model should not compromise accuracy in the pursuit of explainability; and (2) Self-explainable - the model's explanations should truly reflect its decision-making process, not generated from post-hoc methods. The core of ECF is mining taste clusters from user-item interactions and item profiles.We map each user and item to a sparse set of taste clusters, and taste clusters are distinguished by a few representative tags. The user-item preference, users/items' cluster affiliations, and the generation of taste clusters are jointly optimized in an end-to-end manner. Additionally, we introduce a forest mechanism to ensure the model's accuracy, explainability, and diversity. To comprehensively evaluate the explainability quality of taste clusters, we design several quantitative metrics, including in-cluster item coverage, tag utilization, silhouette, and informativeness. Our model's effectiveness is demonstrated through extensive experiments on three real-world datasets.

cs.IR↗

arXiv2023

SEA: A Scalable Entity Alignment System

Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). State-of-the-art EA approaches generally use Graph Neural Networks (GNNs) to encode entities. However, most of them train the models and evaluate the results in a fullbatch fashion, which prohibits EA from being scalable on largescale datasets. To enhance the usability of GNN-based EA models in real-world applications, we present SEA, a scalable entity alignment system that enables to (i) train large-scale GNNs for EA, (ii) speed up the normalization and the evaluation process, and (iii) report clear results for users to estimate different models and parameter settings. SEA can be run on a computer with merely one graphic card. Moreover, SEA encompasses six state-of-the-art EA models and provides access for users to quickly establish and evaluate their own models. Thus, SEA allows users to perform EA without being involved in tedious implementations, such as negative sampling and GPU-accelerated evaluation. With SEA, users can gain a clear view of the model performance. In the demonstration, we show that SEA is user-friendly and is of high scalability even on computers with limited computational resources.

cs.CL↗

arXiv2023

Angle-Uniform Parallel Coordinates

We present angle-uniform parallel coordinates, a data-independent technique that deforms the image plane of parallel coordinates so that the angles of linear relationships between two variables are linearly mapped along the horizontal axis of the parallel coordinates plot. Despite being a common method for visualizing multidimensional data, parallel coordinates are ineffective for revealing positive correlations since the associated parallel coordinates points of such structures may be located at infinity in the image plane and the asymmetric encoding of negative and positive correlations may lead to unreliable estimations. To address this issue, we introduce a transformation that bounds all points horizontally using an angle-uniform mapping and shrinks them vertically in a structure-preserving fashion; polygonal lines become smooth curves and a symmetric representation of data correlations is achieved. We further propose a combined subsampling and density visualization approach to reduce visual clutter caused by overdrawing. Our method enables accurate visual pattern interpretation of data correlations, and its data-independent nature makes it applicable to all multidimensional datasets. The usefulness of our method is demonstrated using examples of synthetic and real-world datasets.

cs.GR↗

arXiv2023

Spatio-Temporal Trajectory Similarity Measures: A Comprehensive Survey and Quantitative Study

Spatio-temporal trajectory analytics is at the core of smart mobility solutions, which offers unprecedented information for diversified applications such as urban planning, infrastructure development, and vehicular networks. Trajectory similarity measure, which aims to evaluate the distance between two trajectories, is a fundamental functionality of trajectory analytics. In this paper, we propose a comprehensive survey that investigates all the most common and representative spatio-temporal trajectory measures. First, we provide an overview of spatio-temporal trajectory measures in terms of three hierarchical perspectives: Non-learning vs. Learning, Free Space vs. Road Network, and Standalone vs. Distributed. Next, we present an evaluation benchmark by designing five real-world transformation scenarios. Based on this benchmark, extensive experiments are conducted to study the effectiveness, robustness,nefficiency, and scalability of each measure, which offers guidelines for trajectory measure selection among multiple techniques and applications such as trajectory data mining, deep learning, and distributed processing.

cs.DS↗

arXiv2023

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an object field component to learn unique codes for all individual objects in 3D space only from 2D supervision. The key to this component is a series of carefully designed loss functions to enable every 3D point, especially in non-occupied space, to be effectively optimized even without 3D labels. In addition, we introduce an inverse query algorithm to freely manipulate any specified 3D object shape in the learned scene representation. Notably, our manipulation algorithm can explicitly tackle key issues such as object collisions and visual occlusions. Our method, called DM-NeRF, is among the first to simultaneously reconstruct, decompose, manipulate and render complex 3D scenes in a single pipeline. Extensive experiments on three datasets clearly show that our method can accurately decompose all 3D objects from 2D views, allowing any interested object to be freely manipulated in 3D space such as translation, rotation, size adjustment, and deformation.

cs.CV↗

arXiv2023

Molecular chaos in dense active systems

The hypothesis of molecular chaos plays the central role in kinetic theory, which provides a closure leading to the Boltzmann equation for quantitative description of classic fluids. Yet how to properly extend it to active systems is still an open question in nonequilibrium physics. Combining experiment, simulation, and theory, we investigate the emergent collective behaviors of self-propelled particles that exhibit collision avoidance, a moving strategy commonly adopted in natural and engineering active systems. This dense active system shows unusual phase dynamics strongly regulated by many-body interactions, which cannot be explained by theories assuming molecular chaos. To rationalize the interplay between different emergent phases, a simple kinetic model is proposed with a revised molecular chaos hypothesis, which treats the many-body effect implicitly via categorizing different types of particle pair collisions. Our model predicts an optimal growth rate of flocking and illustrates a generic approach for understanding dense active systems.

cond-mat.soft↗

arXiv2023

Bubbling phenomenon for semilinear Neumann elliptic equations of critical exponential growth

In the past few decades, much attention has been paid to the bubbling problem for semilinear Neumann elliptic equation with the critical and subcritical polynomial nonlinearity, much less is known if the polynomial nonlinearity is replaced by the exponential nonlinearity. In this paper, we consider the following semilinear Neumann elliptic problem with the Trudinger-Moser exponential growth: \begin{equation*}\begin{cases} -dΔu_d+u_d=u_d(e^{u^2_{d}}-1)\ \ \mbox{in}\ Ω,\\ \frac{\partial u_d}{\partialν}=0\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \mbox{on}\ \partial Ω,\\ \end{cases}\end{equation*} where $d>0$ is a parameter, $Ω$ is a smooth bounded domain in $\mathbb{R}^2$, $ν$ is the unit outer normal to $\partial Ω$. We first prove the existence of a ground state solution to the above equation. If $d$ is sufficiently small, we prove that any ground state solution $u_d$ has at most one maximum point which is located on the boundary of $Ω$ and characterize the shape of ground state solution $u_d$ around the condensation point $P_d$. The key point of the proof lies in proving that the maximum point $P_d$ is close to the boundary at the speed of $\sqrt{d}$ when $d\rightarrow0$ and $u_d$ under suitable scaling transform converges strongly to the ground state solution of the limit equation $Δw+w=w(e^{w^2}-1)$. Our proof is based on the energy threshold of cut-off function, the concentration compactness principle for the Trudinger-Moser inequality, regularity theory for elliptic equation and an accurate analysis for the energy of the ground state solution $u_d$ as $d\rightarrow0$. Furthermore, by assuming that $Ω$ is a unit disk, we remove the smallness assumption on $d$ and show the maximum point of ground state solution $u_d$ must lie on the boundary of $Ω$ for any $d>0$.

math.AP↗

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

Impurity-induced phonon thermal Hall effect in the antiferromagnetic phase of Sr2IrO4

A thermal Hall effect is observed in an increasing number of insulators often attributed to phonons, but the underlying mechanism is in most cases unknown. A coupling of phonons to spins has been invoked and scattering of phonons by impurities or defects has been proposed, but there is no systematic evidence to support either scenario. Here we present a study on the effect of adding Rh impurities to the antiferromagnetic insulator Sr2IrO4, substituting for the spin-carrying Ir atoms. We find that adding small concentrations of Rh impurities increases the thermal Hall conductivity dramatically, but adding enough Rh to suppress the magnetic order eventually decreases the thermal Hall conductivity until it nearly vanishes. We conclude that the thermal Hall effect in this material is caused by the scattering of phonons by impurities embedded within a magnetic environment.

cond-mat.str-el↗

arXiv2023

Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation

We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together. Based on the MAD paradigm, we design a multiple thinking (MT) model that leverages distinct thinking to abstract various meta-abilities. Our method decouples meta-abilities from three aspects: input, encoding, and reward while employing the multiple thinking collaboration (MTC) module to promote mutual cooperation between thinking. MAD introduces a novel qualitative and quantitative interpretability system for object navigation. Through extensive experiments on AI2-Thor and RoboTHOR, we demonstrate that our method outperforms state-of-the-art (SOTA) methods on both typical and zero-shot object navigation tasks.

cs.RO↗

arXiv2023

Magnetic field effects on the quantum spin liquid behaviors of NaYbS$_2$

Spin-orbit coupling is an important ingredient to regulate the many-body physics, especially for many spin liquid candidate materials such as rare-earth magnets and Kitaev materials. The rare-earth chalcogenides NaYbCh$_2$ (Ch = O, S, Se) is a congenital frustrating system to exhibit the intrinsic landmark of spin liquid by eliminating both the site disorders between Na$^{+}$ and Yb$^{3+}$ ions with the big ionic size difference and the Dzyaloshinskii-Moriya interaction with the perfect triangular lattice of the Yb$^{3+}$ ions. The temperature versus magnetic-field phase diagram is established by the magnetization, specific heat, and neutron-scattering measurements. Notably, the neutron diffraction spectra and the magnetization curve might provide microscopic evidence for a series of spin configuration for in-plane fields, which include the disordered spin liquid state, 120$^{o}$ antiferromagnet, and one-half magnetization state. Furthermore, the ground state is suggested to be a gapless spin liquid from inelastic neutron scattering, and the magnetic field adjusts the spin orbit coupling. Therefore, the strong spin-orbit coupling in the frustrated quantum magnet substantially enriches low-energy spin physics. This rare-earth family could offer a good platform for exploring the quantum spin liquid ground state and quantum magnetic transitions.

cond-mat.str-el↗

arXiv2023

On the Structural Generalization in Text-to-SQL

Exploring the generalization of a text-to-SQL parser is essential for a system to automatically adapt the real-world databases. Previous works provided investigations focusing on lexical diversity, including the influence of the synonym and perturbations in both natural language questions and databases. However, research on the structure variety of database schema~(DS) is deficient. Specifically, confronted with the same input question, the target SQL is probably represented in different ways when the DS comes to a different structure. In this work, we provide in-deep discussions about the structural generalization of text-to-SQL tasks. We observe that current datasets are too templated to study structural generalization. To collect eligible test data, we propose a framework to generate novel text-to-SQL data via automatic and synchronous (DS, SQL) pair altering. In the experiments, significant performance reduction when evaluating well-trained text-to-SQL models on the synthetic samples demonstrates the limitation of current research regarding structural generalization. According to comprehensive analysis, we suggest the practical reason is the overfitting of (NL, SQL) patterns.

cs.AI↗

arXiv2022

Estimator: An Effective and Scalable Framework for Transportation Mode Classification over Trajectories

Transportation mode classification, the process of predicting the class labels of moving objects transportation modes, has been widely applied to a variety of real world applications, such as traffic management, urban computing, and behavior study. However, existing studies of transportation mode classification typically extract the explicit features of trajectory data but fail to capture the implicit features that affect the classification performance. In addition, most of the existing studies also prefer to apply RNN-based models to embed trajectories, which is only suitable for classifying small-scale data. To tackle the above challenges, we propose an effective and scalable framework for transportation mode classification over GPS trajectories, abbreviated Estimator. Estimator is established on a developed CNN-TCN architecture, which is capable of leveraging the spatial and temporal hidden features of trajectories to achieve high effectiveness and efficiency. Estimator partitions the entire traffic space into disjointed spatial regions according to traffic conditions, which enhances the scalability significantly and thus enables parallel transportation classification. Extensive experiments using eight public real-life datasets offer evidence that Estimator i) achieves superior model effectiveness (i.e., 99% Accuracy and 0.98 F1-score), which outperforms state-of-the-arts substantially; ii) exhibits prominent model efficiency, and obtains 7-40x speedups up over state-of-the-arts learning-based methods; and iii) shows high model scalability and robustness that enables large-scale classification analytics.

cs.LG↗

arXiv2022

META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI

Task-oriented dialogue (TOD) systems have been widely used by mobile phone intelligent assistants to accomplish tasks such as calendar scheduling or hotel reservation. Current TOD systems usually focus on multi-turn text/speech interaction, then they would call back-end APIs designed for TODs to perform the task. However, this API-based architecture greatly limits the information-searching capability of intelligent assistants and may even lead to task failure if TOD-specific APIs are not available or the task is too complicated to be executed by the provided APIs. In this paper, we propose a new TOD architecture: GUI-based task-oriented dialogue system (GUI-TOD). A GUI-TOD system can directly perform GUI operations on real APPs and execute tasks without invoking TOD-specific backend APIs. Furthermore, we release META-GUI, a dataset for training a Multi-modal convErsaTional Agent on mobile GUI. We also propose a multi-model action prediction and response model, which show promising results on META-GUI. The dataset, codes and leaderboard are publicly available.

cs.CL↗