arXiv subjects
Publications and source records attributed to Jiayu Liu.
In this paper, we proposed a monotone block coordinate descent method for solving absolute value equation (AVE). Under appropriate conditions, we analyzed the global convergence of the algorithm and conduct numerical experiments to demonstrate its feasibility and effectiveness.
Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find that few-shot demonstrations can sometimes bring negative performance and their effectiveness on LLMs' reasoning abilities remains unreliable. To this end, in this paper, we aim to theoretically analyze the impact of in-context demonstrations on LLMs' reasoning performance. We prove that the reasoning efficacy (measured by empirical prediction loss) can be bounded by a LLM-oriented semantic similarity and an inference stability of demonstrations, which is general for both one-shot and few-shot scenarios. Based on this finding, we propose a straightforward, generalizable, and low-complexity demonstration selection method named LMS3. It can adaptively facilitate to select the most pertinent samples for different LLMs and includes a novel demonstration rejection mechanism to automatically filter out samples that are unsuitable for few-shot learning. Through experiments on three representative benchmarks, two LLM backbones, and multiple few-shot settings, we verify that our LMS3 has superiority and achieves consistent improvements on all datasets, which existing methods have been unable to accomplish.
Federated Learning (FL) is an innovative distributed machine learning paradigm that enables neural network training across devices without centralizing data. While this addresses issues of information sharing and data privacy, challenges arise from data heterogeneity across clients and increasing network scale, leading to impacts on model performance and training efficiency. Previous research shows that in IID environments, the parameter structure of the model is expected to adhere to certain specific consistency principles. Thus, identifying and regularizing these consistencies can mitigate issues from heterogeneous data. We found that both soft labels derived from knowledge distillation and the classifier head parameter matrix, when multiplied by their own transpose, capture the intrinsic relationships between data classes. These shared relationships suggest inherent consistency. Therefore, the work in this paper identifies the consistency between the two and leverages it to regulate training, underpinning our proposed FedDW framework. Experimental results show FedDW outperforms 10 state-of-the-art FL methods, improving accuracy by an average of 3% in highly heterogeneous settings. Additionally, we provide a theoretical proof that FedDW offers higher efficiency, with the additional computational load from backpropagation being negligible. The code is available at https://github.com/liuvvvvv1/FedDW.
Measures of textual similarity and divergence are increasingly used to study cultural change. But which measures align, in practice, with social evidence about change? We apply three different representations of text (topic models, document embeddings, and word-level perplexity) to three different corpora (literary studies, economics, and fiction). In every case, works by highly-cited authors and younger authors are textually ahead of the curve. We don't find clear evidence that one representation of text is to be preferred over the others. But alignment with social evidence is strongest when texts are represented through the top quartile of passages, suggesting that a text's impact may depend more on its most forward-looking moments than on sustaining a high level of innovation throughout.
Altermagnetism (AM), a newly discovered magnetic state, ingeniously integrates the properties of ferromagnetism and antiferromagnetism, representing a significant breakthrough in the field of magnetic materials. Despite experimental verification of some typical AM materials, such as MnTe and MnTe$_2$, the pursuit of AM materials that feature larger spin splitting and higher transition temperature is still essential. Here, our research focuses on CrSb, which possesses N{é}el temperature of up to 700K and giant spin splitting near the Fermi level ($E_F$). Utilizing high-resolution angle-resolved photoemission spectroscopy and density functional theory calculations, we meticulously map the three-dimensional electronic structure of CrSb. Our photoemission spectroscopic results on both (0001) and (10$\overline{1}$0) cleavages of CrSb collaboratively reveal unprecedented details on AM-induced band splitting, and subsequently pin down its unique bulk $g$-wave symmetry through quantitative analysis of the angular and photon-energy dependence of spin splitting. Moreover, the observed spin splitting reaches the magnitude of 0.93~eV near $E_F$, the most substantial among all confirmed AM materials. This study not only validates the nature of CrSb as a prototype $g$-wave like AM material but also underscores its pivotal role in pioneering applications in spintronics.
Anomaly detection is a long-standing challenge in manufacturing systems. Traditionally, anomaly detection has relied on human inspectors. However, 3D point clouds have gained attention due to their robustness to environmental factors and their ability to represent geometric data. Existing 3D anomaly detection methods generally fall into two categories. One compares scanned 3D point clouds with design files, assuming these files are always available. However, such assumptions are often violated in many real-world applications where model-free products exist, such as fresh produce (i.e., ``Cookie", ``Potato", etc.), dentures, bone, etc. The other category compares patches of scanned 3D point clouds with a library of normal patches named memory bank. However, those methods usually fail to detect incomplete shapes, which is a fairly common defect type (i.e., missing pieces of different products). The main challenge is that missing areas in 3D point clouds represent the absence of scanned points. This makes it infeasible to compare the missing region with existing point cloud patches in the memory bank. To address these two challenges, we proposed a unified, unsupervised 3D anomaly detection framework capable of identifying all types of defects on model-free products. Our method integrates two detection modules: a feature-based detection module and a reconstruction-based detection module. Feature-based detection covers geometric defects, such as dents, holes, and cracks, while the reconstruction-based method detects missing regions. Additionally, we employ a One-class Support Vector Machine (OCSVM) to fuse the detection results from both modules. The results demonstrate that (1) our proposed method outperforms the state-of-the-art methods in identifying incomplete shapes and (2) it still maintains comparable performance with the SOTA methods in detecting all other types of anomalies.
Rutile RuO$_2$ has been posited as a potential $d$-wave altermagnetism candidate, with a predicted significant spin splitting up to 1.4 eV. Despite accumulating theoretical predictions and transport measurements, direct spectroscopic observation of spin splitting has remained elusive. Here, we employ spin- and angle-resolved photoemission spectroscopy to investigate the band structures and spin polarization of thin-film and single-crystal RuO$_2$. Contrary to expectations of altermagnetism, our analysis indicates that RuO$_2$'s electronic structure aligns with those predicted under non-magnetic conditions, exhibiting no evidence of the hypothesized spin splitting. Additionally, we observe significant in-plane spin polarization of the low-lying bulk bands, which is antisymmetric about the high-symmetry plane and contrary to the $d$-wave spin texture due to time-reversal symmetry breaking in altermagnetism. These findings definitively challenge the altermagnetic order previously proposed for rutile RuO$_2$, prompting a reevaluation of its magnetic properties.
In recent years, the breakthrough of Large Language Models (LLMs) offers new ideas for achieving universal methods on graph data. The common practice of converting graphs into natural language for LLMs, which refers to graph flattening, exhibits good generalizability and interpretability. However, the poor organization of the textual format results in poor performance in long-distance scenario understanding. Inspired by human cognitive reasoning habits, we propose a novel method for graph flattening to fit LLMs, termed as End-to-End DAG-Path prompting (EEDP). Experiments on real-world datasets show that EEDP enhances the reasoning performance of LLMs in long-distance scenarios while maintaining excellent performance in short-distance scenarios, demonstrating good robustness in the face of distance variations.
Studying and building datasets for dialogue tasks is both expensive and time-consuming due to the need to recruit, train, and collect data from study participants. In response, much recent work has sought to use large language models (LLMs) to simulate both human-human and human-LLM interactions, as they have been shown to generate convincingly human-like text in many settings. However, to what extent do LLM-based simulations \textit{actually} reflect human dialogues? In this work, we answer this question by generating a large-scale dataset of 100,000 paired LLM-LLM and human-LLM dialogues from the WildChat dataset and quantifying how well the LLM simulations align with their human counterparts. Overall, we find relatively low alignment between simulations and human interactions, demonstrating a systematic divergence along the multiple textual properties, including style and content. Further, in comparisons of English, Chinese, and Russian dialogues, we find that models perform similarly. Our results suggest that LLMs generally perform better when the human themself writes in a way that is more similar to the LLM's own style.
Educational resource understanding is vital to online learning platforms, which have demonstrated growing applications recently. However, researchers and developers always struggle with using existing general natural language toolkits or domain-specific models. The issue raises a need to develop an effective and easy-to-use one that benefits AI education-related research and applications. To bridge this gap, we present a unified, modularized, and extensive library, EduNLP, focusing on educational resource understanding. In the library, we decouple the whole workflow to four key modules with consistent interfaces including data configuration, processing, model implementation, and model evaluation. We also provide a configurable pipeline to unify the data usage and model usage in standard ways, where users can customize their own needs. For the current version, we primarily provide 10 typical models from four categories, and 5 common downstream-evaluation tasks in the education domain on 8 subjects for users' usage. The project is released at: https://github.com/bigdata-ustc/EduNLP.
In this paper, we reconsider two new iterative methods for solving absolute value equations (AVE), which is proposed by Ali and Pan (Jpn. J. Ind. Appl. Math. 40: 303--314, 2023). Convergence results of the two iterative schemes and new sufficient conditions for the unique solvability of AVE are presented. In addition, for a special case, the optimal iteration parameters of the two algorithms are analyzed, respectively. Numerical results demonstrate our claims.
Geometry Problem Solving (GPS), which is a classic and challenging math problem, has attracted much attention in recent years. It requires a solver to comprehensively understand both text and diagram, master essential geometry knowledge, and appropriately apply it in reasoning. However, existing works follow a paradigm of neural machine translation and only focus on enhancing the capability of encoders, which neglects the essential characteristics of human geometry reasoning. In this paper, inspired by dual-process theory, we propose a Dual-Reasoning Geometry Solver (DualGeoSolver) to simulate the dual-reasoning process of humans for GPS. Specifically, we construct two systems in DualGeoSolver, namely Knowledge System and Inference System. Knowledge System controls an implicit reasoning process, which is responsible for providing diagram information and geometry knowledge according to a step-wise reasoning goal generated by Inference System. Inference System conducts an explicit reasoning process, which specifies the goal in each reasoning step and applies the knowledge to generate program tokens for resolving it. The two systems carry out the above process iteratively, which behaves more in line with human cognition. We conduct extensive experiments on two benchmark datasets, GeoQA and GeoQA+. The results demonstrate the superiority of DualGeoSolver in both solving accuracy and robustness from explicitly modeling human reasoning process and knowledge application.
Revealing the momentum-resolved electronic structure of infinite-layer nickelates is essential for understanding this new class of unconventional superconductors, but has been hindered by the formidable challenges in improving the sample quality. In this work, we report for the first time the angle-resolved photoemission spectroscopy of superconducting La$_{0.8}$Sr$_{0.2}$NiO$_{2}$ films prepared by molecular beam epitaxy and ${\mathrm{\textit{in situ}}}$ atomic-hydrogen reduction. The measured Fermi topology closely matches theoretical calculations, showing a large Ni-$d_{x^2-y^2}$ derived Fermi sheet that evolves from hole-like to electron-like along $k_{z}$, and a three-dimensional (3D) electron pocket centered at Brillouin zone corner. The Ni-$d_{x^2-y^2}$ derived bands show a mass enhancement ($m^*/m_{\rm{DFT}}$) of 2-3,while the 3D electron band shows negligible band renormalization. Moreover, the Ni-$d_{x^2-y^2}$ derived states also display a band dispersion anomaly at higher binding energy, reminiscent of the waterfall feature and kinks observed in cuprates.
Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://github.com/hly1998/BRCD.
Personalized learner modeling using cognitive diagnosis (CD), which aims to model learners' cognitive states by diagnosing learner traits from behavioral data, is a fundamental yet significant task in many web learning services. Existing cognitive diagnosis models (CDMs) follow the proficiency-response paradigm that views learner traits and question parameters as trainable embeddings and learns them through learner performance prediction. However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners' cognitive states and the quality of web learning services. To address these problems, we propose an identifiable cognitive diagnosis framework (ID-CDF) based on a novel response-proficiency-response paradigm inspired by encoder-decoder models. Specifically, we first devise the diagnostic module of ID-CDF, which leverages inductive learning to eliminate randomness in optimization to guarantee identifiability and captures the monotonicity between overall response data distribution and cognitive states to prevent explainability overfitting. Next, we propose a flexible predictive module for ID-CDF to ensure diagnosis preciseness. We further present an implementation of ID-CDF, i.e., ID-CDM, to illustrate its usability. Extensive experiments on four real-world datasets with different characteristics demonstrate that ID-CDF can effectively address the problems without loss of diagnosis preciseness.
Magnetic topological quantum materials display a diverse range of fascinating physical properties which arise from their intrinsic magnetism and the breaking of time-reversal symmetry. However, so far, few examples of intrinsic magnetic topological materials have been confirmed experimentally, which significantly hinder our comprehensive understanding of the abundant physical properties in this system. The kagome lattices, which host diversity of electronic structure signatures such as Dirac nodes, flat bands, and saddle points, provide an alternative and promising platform for in-depth investigations into correlations and band topology. In this article, drawing inspiration from the stacking configuration of MnBi$_2$Te$_4$, we conceive and then synthesize a high-quality single crystal EuTi$_3$Bi$_4$, which is a unique natural heterostructure consisting of both topological kagome layers and magnetic interlayers. We investigate the electronic structure of EuTi$_3$Bi$_4$ and uncover distinct features of anisotropic multiple Van Hove singularitie (VHS) that might prevent Fermi surface nesting, leading to the absence of a charge density wave (CDW). In addition, we identify the topological nontrivial surface states that serve as connections between different saddle bands in the vicinity of the Fermi level. Combined with calculations, we establish that, the effective time-reversal symmetry S=$θ$$τ_{1/2}$ play a crucial role in the antiferromagnetic ground state of EuTi$_3$Bi$_4$, which ensures the stability of the topological surface states and gives rise to their intriguing topological nature. Therefore, EuTi$_3$Bi$_4$ offers the rare opportunity to investigate correlated topological states in magnetic kagome materials.
Machine learning systems are often applied to data that is drawn from a different distribution than the training distribution. Recent work has shown that for a variety of classification and signal reconstruction problems, the out-of-distribution performance is strongly linearly correlated with the in-distribution performance. If this relationship or more generally a monotonic one holds, it has important consequences. For example, it allows to optimize performance on one distribution as a proxy for performance on the other. In this paper, we study conditions under which a monotonic relationship between the performances of a model on two distributions is expected. We prove an exact asymptotic linear relation for squared error and a monotonic relation for misclassification error for ridge-regularized general linear models under covariate shift, as well as an approximate linear relation for linear inverse problems.
Kagome superconductors AV$_3$Sb$_5$ (A = K, Rb, Cs) provide a fertile playground for studying intriguing phenomena, including non-trivial band topology, superconductivity, giant anomalous Hall effect and charge density wave (CDW). Recently, a $C_2$ symmetric nematic phase prior to the superconducting state in AV$_3$Sb$_5$ drew enormous attention due to its potential inheritance of the symmetry of the unusual superconductivity. However, direct evidence on the rotation symmetry breaking of the electronic structure in the CDW state from the reciprocal space is still rare, and the underlying mechanism remains ambiguous. The observation shows unconventional unidirectionality, indicative of rotation symmetry breaking from six-fold to two-fold. The interlayer coupling between adjacent planes with $π$-phase offset in the 2$\times$2$\times$2 CDW phase leads to the preferred two-fold symmetric electronic structure. These rarely observed unidirectional back-folded bands in KV$_3$Sb$_5$ may provide important insights into its peculiar charge order and superconductivity.