arXiv subjects

Xiang Li

Publications and source records attributed to Xiang Li.

At least 1,099 records · Page 61Linked to original sources

arXiv2022

Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder

In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning problem is one of the most typical and challenging problems. Existing methods usually adopt encoder-decoder framework to represent hybrid contents and generate answers. However, it can not capture the rich relationship among numerical value, table schema, and text information on the encoder side. The decoder uses a simple predefined operator classifier which is not flexible enough to handle numerical reasoning processes with diverse expressions. To address these problems, this paper proposes a \textbf{Re}lational \textbf{G}raph enhanced \textbf{H}ybrid table-text \textbf{N}umerical reasoning model with \textbf{T}ree decoder (\textbf{RegHNT}). It models the numerical question answering over table-text hybrid contents as an expression tree generation task. Moreover, we propose a novel relational graph modeling method, which models alignment between questions, tables, and paragraphs. We validated our model on the publicly available table-text hybrid QA benchmark (TAT-QA). The proposed RegHNT significantly outperform the baseline model and achieve state-of-the-art results. We openly released the source code and data at https://github.com/lfy79001/RegHNT (2022-05-05).

cs.CL↗

arXiv2022

Pixel-Aligned Non-parametric Hand Mesh Reconstruction

Non-parametric mesh reconstruction has recently shown significant progress in 3D hand and body applications. In these methods, mesh vertices and edges are visible to neural networks, enabling the possibility to establish a direct mapping between 2D image pixels and 3D mesh vertices. In this paper, we seek to establish and exploit this mapping with a simple and compact architecture. The network is designed with these considerations: 1) aggregating both local 2D image features from the encoder and 3D geometric features captured in the mesh decoder; 2) decoding coarse-to-fine meshes along the decoding layers to make the best use of the hierarchical multi-scale information. Specifically, we propose an end-to-end pipeline for hand mesh recovery tasks which consists of three phases: a 2D feature extractor constructing multi-scale feature maps, a feature mapping module transforming local 2D image features to 3D vertex features via 3D-to-2D projection, and a mesh decoder combining the graph convolution and self-attention to reconstruct mesh. The decoder aggregate both local image features in pixels and geometric features in vertices. It also regresses the mesh vertices in a coarse-to-fine manner, which can leverage multi-scale information. By exploiting the local connection and designing the mesh decoder, Our approach achieves state-of-the-art for hand mesh reconstruction on the public FreiHAND dataset.

cs.CV↗

arXiv2022

Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding

Knowledge-enhanced Pre-trained Language Model (PLM) has recently received significant attention, which aims to incorporate factual knowledge into PLMs. However, most existing methods modify the internal structures of fixed types of PLMs by stacking complicated modules, and introduce redundant and irrelevant factual knowledge from knowledge bases (KBs). In this paper, to address these problems, we introduce a seminal knowledge prompting paradigm and further propose a knowledge-prompting-based PLM framework KP-PLM. This framework can be flexibly combined with existing mainstream PLMs. Specifically, we first construct a knowledge sub-graph from KBs for each context. Then we design multiple continuous prompts rules and transform the knowledge sub-graph into natural language prompts. To further leverage the factual knowledge from these prompts, we propose two novel knowledge-aware self-supervised tasks including prompt relevance inspection and masked prompt modeling. Extensive experiments on multiple natural language understanding (NLU) tasks show the superiority of KP-PLM over other state-of-the-art methods in both full-resource and low-resource settings.

cs.CL↗

arXiv2022

Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization

Adaptive algorithms like AdaGrad and AMSGrad are successful in nonconvex optimization owing to their parameter-agnostic ability -- requiring no a priori knowledge about problem-specific parameters nor tuning of learning rates. However, when it comes to nonconvex minimax optimization, direct extensions of such adaptive optimizers without proper time-scale separation may fail to work in practice. We provide such an example proving that the simple combination of Gradient Descent Ascent (GDA) with adaptive stepsizes can diverge if the primal-dual stepsize ratio is not carefully chosen; hence, a fortiori, such adaptive extensions are not parameter-agnostic. To address the issue, we formally introduce a Nested Adaptive framework, NeAda for short, that carries an inner loop for adaptively maximizing the dual variable with controllable stopping criteria and an outer loop for adaptively minimizing the primal variable. Such mechanism can be equipped with off-the-shelf adaptive optimizers and automatically balance the progress in the primal and dual variables. Theoretically, for nonconvex-strongly-concave minimax problems, we show that NeAda can achieve the near-optimal $\tilde{O}(ε^{-2})$ and $\tilde{O}(ε^{-4})$ gradient complexities respectively in the deterministic and stochastic settings, without prior information on the problem's smoothness and strong concavity parameters. To the best of our knowledge, this is the first algorithm that simultaneously achieves near-optimal convergence rates and parameter-agnostic adaptation in the nonconvex minimax setting. Numerically, we further illustrate the robustness of the NeAda family with experiments on simple test functions and a real-world application.

math.OC↗

arXiv2022

A Complementary Framework for Human-Robot Collaboration with a Mixed AR-Haptic Interface

There is invariably a trade-off between safety and efficiency for collaborative robots (cobots) in human-robot collaborations. Robots that interact minimally with humans can work with high speed and accuracy but cannot adapt to new tasks or respond to unforeseen changes, whereas robots that work closely with humans can but only by becoming passive to humans, meaning that their main tasks suspended and efficiency compromised. Accordingly, this paper proposes a new complementary framework for human-robot collaboration that balances the safety of humans and the efficiency of robots. In this framework, the robot carries out given tasks using a vision-based adaptive controller, and the human expert collaborates with the robot in the null space. Such a decoupling drives the robot to deal with existing issues in task space (e.g., uncalibrated camera, limited field of view) and in null space (e.g., joint limits) by itself while allowing the expert to adjust the configuration of the robot body to respond to unforeseen changes (e.g., sudden invasion, change of environment) without affecting the robot's main task. Additionally, the robot can simultaneously learn the expert's demonstration in task space and null space beforehand with dynamic movement primitives (DMP). Therefore, an expert's knowledge and a robot's capability are both explored and complementary. Human demonstration and involvement are enabled via a mixed interaction interface, i.e., augmented reality (AR) and haptic devices. The stability of the closed-loop system is rigorously proved with Lyapunov methods. Experimental results in various scenarios are presented to illustrate the performance of the proposed method.

cs.RO↗

arXiv2022

Probabilistic Inverse Modeling: An Application in Hydrology

The astounding success of these methods has made it imperative to obtain more explainable and trustworthy estimates from these models. In hydrology, basin characteristics can be noisy or missing, impacting streamflow prediction. For solving inverse problems in such applications, ensuring explainability is pivotal for tackling issues relating to data bias and large search space. We propose a probabilistic inverse model framework that can reconstruct robust hydrology basin characteristics from dynamic input weather driver and streamflow response data. We address two aspects of building more explainable inverse models, uncertainty estimation and robustness. This can help improve the trust of water managers, handling of noisy data and reduce costs. We propose uncertainty based learning method that offers 6\% improvement in $R^2$ for streamflow prediction (forward modeling) from inverse model inferred basin characteristic estimates, 17\% reduction in uncertainty (40\% in presence of noise) and 4\% higher coverage rate for basin characteristics.

cs.LG↗

arXiv2022

Linear Optical Modulators for Prospective Communications at the 2 μm Waveband

The 2 μm waveband is an area that could have significant technological consequences, with applications ranging from spectroscopy, LIDAR and free-space communications. The development of the thulium-doped fiber amplifier, hollow-core photonic bandgap fiber and 2 μm GaSb-based diode lasers has highlighted the ability of the waveband in alleviating the fiber capacity crisis in the incumbent communication infrastructure. The above has initiated vibrant development in the silicon photonic-space at 2 μm, where the area is capable of enabling highly-integrated photonic circuits, and potentially at low-cost and high-volumes. However, as of now, modulator linearity at 2 μm has not been addressed. The metric, as characterized by spurious free dynamic range is imperative for numerous applications such as RF photonic links for 5G and digital analog transmission in coherent communications. The development of linear optical modulators will be crucial in bringing these applications to the 2 μm. In view of that, this work is the first to address modulator linearity at the 2 μm, where the ring-assisted Mach-Zehnder modulator is developed, indicating spurious free dynamic range as high as 95 dB.Hz^2/3. It is found that that modulator spurious free dynamic range has a strong dependence on modulator bias voltage where it impacts the linearity of the transfer function in which the input RF signal is applied upon. The demonstrated modulator indicates favorable performance within silicon photonic modulators developed at 2 μm with bandwidth exceeding 17.5 GHz and modulation efficiency ranging from 0.70 to 1.25 V.cm.

physics.app-ph↗

arXiv2022

Gauge independent description of Aharonov-Bohm Effect

The Aharonov-Bohm (AB) effect is a pure quantum effect that implies a measurable phase shift in the wave function for a charged particle that encircles a magnetic flux located in a region \textit{inaccessible} to the particle. Classically, such a non-local effect appears to be impossible since the Lorentz force depends on only the magnetic field at the location of the particle. In quantum mechanics, the Hamiltonian, and thus the Schrödinger equation, has a local coupling between the current due to the particle, and the electromagnetic vector potential $\mathbf{A}$, which extends to the entire space beyond the region with finite magnetic field. This has sometimes been interpreted as meaning that in quantum mechanics $\mathbf{A}$ is in some sense more "fundamental" than $\mathbf {B}$ in spite of the former being gauge dependent, and thus unobservable. Here we shall, with a general proof followed by a few examples, demonstrate that the AB-effect can be fully accounted for by considering only the gauge invariant $\mathbf{B}$ field, as long as it is included as part of the quantum action of the entire isolated system. The price for the gauge invariant formulation is that we must give up locality -- the AB-phase for the particle will arise from the change in the action for the $\mathbf{B}$ field in the region inaccessible to the particle.

quant-ph↗

arXiv2022

CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction

Quotation extraction aims to extract quotations from written text. There are three components in a quotation: source refers to the holder of the quotation, cue is the trigger word(s), and content is the main body. Existing solutions for quotation extraction mainly utilize rule-based approaches and sequence labeling models. While rule-based approaches often lead to low recalls, sequence labeling models cannot well handle quotations with complicated structures. In this paper, we propose the Context and Former-Label Enhanced Net (CofeNet) for quotation extraction. CofeNet is able to extract complicated quotations with components of variable lengths and complicated structures. On two public datasets (i.e., PolNeAR and Riqua) and one proprietary dataset (i.e., PoliticsZH), we show that our CofeNet achieves state-of-the-art performance on complicated quotation extraction.

cs.CL↗

arXiv2022

Study of the Global Alignment for the DAMPE Detector

The Dark Matter Particle Explorer (DAMPE) is designed as a high energy particle detector for probing cosmic-rays and $γ-$rays in a wide energy range. The trajectory of the incident particle is mainly measured by the Silicon-Tungsten tracKer-converter (STK) sub-detector, which heavily depends on the precise internal alignment correction as well as the accuracy of the global coordinate system. In this work, we carried out a global alignment method to validate the potential displacement of these sub-detectors, and particularly demonstrated that the track reconstruction of STK can well satisfy the required objectives by means of comparing flight data and simulations.

physics.ins-det↗

arXiv2022

Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extraction

Emotion-cause pair extraction (ECPE) is an emerging task aiming to extract potential pairs of emotions and corresponding causes from documents. Previous approaches have focused on modeling the pair-to-pair relationship and achieved promising results. However, the clause-to-clause relationship, which fundamentally symbolizes the underlying structure of a document, has still been in its research infancy. In this paper, we define a novel clause-to-clause relationship. To learn it applicably, we propose a general clause-level encoding model named EA-GAT comprising E-GAT and Activation Sort. E-GAT is designed to aggregate information from different types of clauses; Activation Sort leverages the individual emotion/cause prediction and the sort-based mapping to propel the clause to a more favorable representation. Since EA-GAT is a clause-level encoding model, it can be broadly integrated with any previous approach. Experimental results show that our approach has a significant advantage over all current approaches on the Chinese and English benchmark corpus, with an average of $2.1\%$ and $1.03\%$.

cs.CL↗

arXiv2022

Global Model Learning for Large Deformation Control of Elastic Deformable Linear Objects: An Efficient and Adaptive Approach

Robotic manipulation of deformable linear objects (DLOs) has broad application prospects in many fields. However, a key issue is to obtain the exact deformation models (i.e., how robot motion affects DLO deformation), which are hard to theoretically calculate and vary among different DLOs. Thus, shape control of DLOs is challenging, especially for large deformation control which requires global and more accurate models. In this paper, we propose a coupled offline and online data-driven method for efficiently learning a global deformation model, allowing for both accurate modeling through offline learning and further updating for new DLOs via online adaptation. Specifically, the model approximated by a neural network is first trained offline on random data, then seamlessly migrated to the online phase, and further updated online during actual manipulation. Several strategies are introduced to improve the model's efficiency and generalization ability. We propose a convex-optimization-based controller, and analyze the system's stability using the Lyapunov method. Detailed simulations and real-world experiments demonstrate that our method can efficiently and precisely estimate the deformation model, and achieve large deformation control of untrained DLOs in 2D and 3D dual-arm manipulation tasks better than the existing methods. It accomplishes all 24 tasks with different desired shapes on different DLOs in the real world, using only simulation data for the offline learning.

cs.RO↗

arXiv2022

Towards Cross-speaker Reading Style Transfer on Audiobook Dataset

Cross-speaker style transfer aims to extract the speech style of the given reference speech, which can be reproduced in the timbre of arbitrary target speakers. Existing methods on this topic have explored utilizing utterance-level style labels to perform style transfer via either global or local scale style representations. However, audiobook datasets are typically characterized by both the local prosody and global genre, and are rarely accompanied by utterance-level style labels. Thus, properly transferring the reading style across different speakers remains a challenging task. This paper aims to introduce a chunk-wise multi-scale cross-speaker style model to capture both the global genre and the local prosody in audiobook speeches. Moreover, by disentangling speaker timbre and style with the proposed switchable adversarial classifiers, the extracted reading style is made adaptable to the timbre of different speakers. Experiment results confirm that the model manages to transfer a given reading style to new target speakers. With the support of local prosody and global genre type predictor, the potentiality of the proposed method in multi-speaker audiobook generation is further revealed.

cs.SD↗

arXiv2022

Influence of impurities on electronic structure in cuprate superconductors

The impurity is inherently manifest in cuprate superconductors, as cation substitution or intercalation is necessary for the introduction of charge carriers, and its influence on the electronic state is at the heart of a great debate in physics. Here based on the microscopic octet scattering model, the influence of the impurity scattering on the electronic structure of cuprate superconductors is investigated in terms of the self-consistent T-matrix approach. The impurity scattering self-energy is evaluated firstly in the Fermi-arc-tip approximation of the quasiparticle excitations and scattering processes, and the obtained results show that the decisive role played by the impurity scattering self-energy in the particle-hole channel is the further renormalization of the quasiparticle band structure with a reduced quasiparticle lifetime, while the impurity scattering self-energy in the particle-particle channel induces a strong deviation from the d-wave behaviour of the superconducting gap, leading to the existence of a finite gap over the entire electron Fermi surface. Moreover, these impurity scattering self-energies are employed to study the exotic features of the line-shape in the quasiparticle excitation spectrum and the autocorrelation of the quasiparticle excitation spectra, and the obtained results are then compared with the corresponding experimental data. The theory therefore also indicates that the unconventional features of the electronic structure in cuprate superconductors is generated by both the strong electron correlation and impurity scattering.

cond-mat.supr-con↗

arXiv2022

PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection

In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance. To address the problems incurred by noisy pseudo boxes, we design Noisy Pseudo box Learning (NPL) that includes Prediction-guided Label Assignment (PLA) and Positive-proposal Consistency Voting (PCV). PLA relies on model predictions to assign labels and makes it robust to even coarse pseudo boxes; while PCV leverages the regression consistency of positive proposals to reflect the localization quality of pseudo boxes. Furthermore, in consistency training, we propose Multi-view Scale-invariant Learning (MSL) that includes mechanisms of both label- and feature-level consistency, where feature consistency is achieved by aligning shifted feature pyramids between two images with identical content but varied scales. On COCO benchmark, our method, termed PSEudo labeling and COnsistency training (PseCo), outperforms the SOTA (Soft Teacher) by 2.0, 1.8, 2.0 points under 1%, 5%, and 10% labelling ratios, respectively. It also significantly improves the learning efficiency for SSOD, e.g., PseCo halves the training time of the SOTA approach but achieves even better performance. Code is available at https://github.com/ligang-cs/PseCo.

cs.CV↗

arXiv2022

High-pressure control of optical nonlinearity in the polar Weyl semimetal TaAs

The transition metal monopnictide family of Weyl semimetals recently has been shown to exhibit anomalously strong second-order optical nonlinearity, which is theoretically attributed to a highly asymmetric polarization distribution induced by their polar structure. We experimentally test this hypothesis by measuring optical second harmonic generation (SHG) from TaAs across a pressure-tuned polar-to-nonpolar structural phase transition. Despite the high-pressure structure remaining noncentrosymmetric, the SHG yield is reduced by more than 60 % by 20 GPa as compared to the ambient pressure value. By examining the pressure dependence of distinct groups of SHG susceptibility tensor elements, we find that the yield is primarily controlled by a single element that governs the response along the polar axis. Our results confirm a connection between the polar axis and the giant optical nonlinearity of Weyl semimetals and demonstrate pressure as a means to tune this effect $in$ $situ$.

cond-mat.str-el↗

arXiv2022

A density peaks clustering algorithm with sparse search and K-d tree

Density peaks clustering has become a nova of clustering algorithm because of its simplicity and practicality. However, there is one main drawback: it is time-consuming due to its high computational complexity. Herein, a density peaks clustering algorithm with sparse search and K-d tree is developed to solve this problem. Firstly, a sparse distance matrix is calculated by using K-d tree to replace the original full rank distance matrix, so as to accelerate the calculation of local density. Secondly, a sparse search strategy is proposed to accelerate the computation of relative-separation with the intersection between the set of $k$ nearest neighbors and the set consisting of the data points with larger local density for any data point. Furthermore, a second-order difference method for decision values is adopted to determine the cluster centers adaptively. Finally, experiments are carried out on datasets with different distribution characteristics, by comparing with other six state-of-the-art clustering algorithms. It is proved that the algorithm can effectively reduce the computational complexity of the original DPC from $O(n^2K)$ to $O(n(n^{1-1/K}+k))$. Especially for larger datasets, the efficiency is elevated more remarkably. Moreover, the clustering accuracy is also improved to a certain extent. Therefore, it can be concluded that the overall performance of the newly proposed algorithm is excellent.

stat.ML↗

arXiv2022

SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization

Recent advances in data processing have stimulated the demand for learning graphs of very large scales. Graph Neural Networks (GNNs), being an emerging and powerful approach in solving graph learning tasks, are known to be difficult to scale up. Most scalable models apply node-based techniques in simplifying the expensive graph message-passing propagation procedure of GNN. However, we find such acceleration insufficient when applied to million- or even billion-scale graphs. In this work, we propose SCARA, a scalable GNN with feature-oriented optimization for graph computation. SCARA efficiently computes graph embedding from node features, and further selects and reuses feature computation results to reduce overhead. Theoretical analysis indicates that our model achieves sub-linear time complexity with a guaranteed precision in propagation process as well as GNN training and inference. We conduct extensive experiments on various datasets to evaluate the efficacy and efficiency of SCARA. Performance comparison with baselines shows that SCARA can reach up to 100x graph propagation acceleration than current state-of-the-art methods with fast convergence and comparable accuracy. Most notably, it is efficient to process precomputation on the largest available billion-scale GNN dataset Papers100M (111M nodes, 1.6B edges) in 100 seconds.

cs.LG↗