arXiv subjects

Xiaoxuan Wang

Publications and source records attributed to Xiaoxuan Wang.

24 records · Page 2Linked to original sources

arXiv2024

STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models

Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific training data in the form of (passage, target structure) pairs to obtain reasonable performance. However, obtaining such data through human annotation is costly, leading to a pressing need for low-resource information extraction approaches that require minimal human labeling for real-world applications. Fine-tuning supervised models with synthesized training data would be a generalizable method, but the existing data generation methods either still rely on large-scale ground-truth data or cannot be applied to complicated IE tasks due to their poor performance. To address these challenges, we propose STAR, a data generation method that leverages Large Language Models (LLMs) to synthesize data instances given limited seed demonstrations, thereby boosting low-resource information extraction performance. Our approach involves generating target structures (Y) followed by generating passages (X), all accomplished with the aid of LLMs. We design fine-grained step-by-step instructions to obtain the initial data instances. We further reduce errors and improve data quality through self-reflection error identification and self-refinement with iterative revision. Our experiments show that the data generated by STAR significantly improve the performance of low-resource event extraction and relation extraction tasks, even surpassing the effectiveness of human-curated data. Human assessment of the data quality shows STAR-generated data exhibits higher passage quality and better align with the task definitions compared with the human-curated data.

cs.CL↗

arXiv2023

Learning under Label Proportions for Text Classification

We present one of the preliminary NLP works under the challenging setup of Learning from Label Proportions (LLP), where the data is provided in an aggregate form called bags and only the proportion of samples in each class as the ground truth. This setup is inline with the desired characteristics of training models under Privacy settings and Weakly supervision. By characterizing some irregularities of the most widely used baseline technique DLLP, we propose a novel formulation that is also robust. This is accompanied with a learnability result that provides a generalization bound under LLP. Combining this formulation with a self-supervised objective, our method achieves better results as compared to the baselines in almost 87% of the experimental configurations which include large scale models for both long and short range texts across multiple metrics.

cs.LG↗

arXiv2022

Emergent topological states via digital (001) oxide superlattices

Oxide heterostructures exhibit many intriguing properties. Here we provide design principles for inducing multiple topological states in (001) ($AM$O$_3$)$_1$/($AM'$O$_3$)$_1$ oxide superlattices. Aided by first-principles calculations and model analysis, we show that a (Sr$M$O3)$_1$/(Sr$M'$O$_3$)$_1$ superlattice ($M$ = Nb, Ta and $M'$ = Rh, Ir) is a strong topological insulator with $Z_2$ index (1;001). More remarkably, a (SrMoO3)$_1$/(SrIrO3)$_1$ superlattice exhibits multiple coexisting topological insulator (TI) and topological Dirac semi-metal (TDS) states. The TDS state has a pair of type-II Dirac points near the Fermi level and symmetry-protected Dirac node lines. The surface TDS Dirac cone is sandwiched by two surface TI Dirac cones in the energy-momentum space. The non-trivial topological properties arise from the band inversion between $d$ orbitals of two dissimilar transition metal atoms and a particular parity property of (001) superlattice geometry. Our work demonstrates how to induce nontrivial topological states in (001) perovskite oxide heterostructures by rational design.

cond-mat.mtrl-sci↗

arXiv2021

Online Feature Selection for Efficient Learning in Networked Systems

Current AI/ML methods for data-driven engineering use models that are mostly trained offline. Such models can be expensive to build in terms of communication and computing cost, and they rely on data that is collected over extended periods of time. Further, they become out-of-date when changes in the system occur. To address these challenges, we investigate online learning techniques that automatically reduce the number of available data sources for model training. We present an online algorithm called Online Stable Feature Set Algorithm (OSFS), which selects a small feature set from a large number of available data sources after receiving a small number of measurements. The algorithm is initialized with a feature ranking algorithm, a feature set stability metric, and a search policy. We perform an extensive experimental evaluation of this algorithm using traces from an in-house testbed and from a data center in operation. We find that OSFS achieves a massive reduction in the size of the feature set by 1-3 orders of magnitude on all investigated datasets. Most importantly, we find that the accuracy of a predictor trained on a OSFS-produced feature set is somewhat better than when the predictor is trained on a feature set obtained through offline feature selection. OSFS is thus shown to be effective as an online feature selection algorithm and robust regarding the sample interval used for feature selection. We also find that, when concept drift in the data underlying the model occurs, its effect can be mitigated by recomputing the feature set and retraining the prediction model.

cs.LG↗

arXiv2020

Online feature selection for rapid, low-overhead learning in networked systems

Data-driven functions for operation and management often require measurements collected through monitoring for model training and prediction. The number of data sources can be very large, which requires a significant communication and computing overhead to continuously extract and collect this data, as well as to train and update the machine-learning models. We present an online algorithm, called OSFS, that selects a small feature set from a large number of available data sources, which allows for rapid, low-overhead, and effective learning and prediction. OSFS is instantiated with a feature ranking algorithm and applies the concept of a stable feature set, which we introduce in the paper. We perform extensive, experimental evaluation of our method on data from an in-house testbed. We find that OSFS requires several hundreds measurements to reduce the number of data sources by two orders of magnitude, from which models are trained with acceptable prediction accuracy. While our method is heuristic and can be improved in many ways, the results clearly suggests that many learning tasks do not require a lengthy monitoring phase and expensive offline training.

cs.LG↗

arXiv2020

A substantial hybridization between correlated Ni-d orbital and itinerant electrons in infinite-layer nickelates

The discovery of unconventional superconductivity in hole doped NdNiO2, similar to CaCuO2, has received enormous attention. However, different from CaCuO2, RNiO2 (R = Nd, La) has itinerant electrons in the rare-earth spacer layer. Previous studies show that the hybridization between Ni-dx2-y2 and rare-earth-d orbitals is very weak and thus RNiO2 is still a promising analog of CaCuO2. Here, we perform first-principles calculations to show that the hybridization between Ni-dx2-y2 orbital and itinerant electrons in RNiO2 is substantially stronger than previously thought. The dominant hybridization comes from an interstitial-s orbital rather than rare-earth-d orbitals, due to a large inter-cell hopping. Because of the hybridization, Ni local moment is screened by itinerant electrons and the critical U_Ni for long-range magnetic ordering is increased. Our work shows that the electronic structure of RNiO2 is distinct from CaCuO2, implying that the observed superconductivity in infinite-layer nickelates does not emerge from a doped Mott insulator.

cond-mat.str-el↗