arXiv subjects

Wenbo Xie

Publications and source records attributed to Wenbo Xie.

9 recordsLinked to original sources

arXiv2026

Complete O(3) Interactions from Wigner-6j Recoupling to Local O(2) Frames

Equivariant atomistic models commonly use either Clebsch Gordan tensor product(CGTP) or edge aligned SO(2) operationsCGTP support general O(3) representations but become expensive at high angular degree, while existing local SO(2) frame methods are designed for SO(3) or the natural-parity subset of O(3). They therefore do not provide a complete local representation when polar tensors and pseudotensors occur at the same time. In this work, we introduce a generalized Wigner-6j convolution for non-collinear magnetism, electric fields, and magnetic fields, providing a general convolution scheme under O(3) that can incorporate arbitrary node-wise equivariant features. We further develop a complete O(3) convolution framework based on local O(2) frames, reducing the computational complexity of CGTPs from O(L6) to O(L3). We establish the correspondence between global O(3) irreducible representations (irreps) and local O(2) irreps and use this correspondence to construct a closed operator system comprising O2Linear, O2TensorProduct, and O2Gate.

physics.chem-ph↗

arXiv2026

Edge Cluster Expansion with Radial Rotary Attention for Interatomic Potentials

In this paper, we provide a systematic investigation of SO(2) theory to machine learning interatomic potentials (MLIPs) and identify the limitations of conventional SO(2) Linear architectures relative to SO(3) Clebsch-Gordan Tensor Products (CGTP). Building on these insights, we propose direct Cartesian construction and recursive Clebsch-Gordan construction of Wigner D-matrices and introduce two novel interaction building blocks. First, we propose the Edge Complex Product Basis based on Generalized Asymmetric Contraction, a new formulation for many-body expansion that directly constructs higher-order interactions on edges through complex-valued equivariant multiplications. Second, we introduce Radial Rotary Complex Attention(RRA), which enhances extrapolation performance and surpasses existing attention vector formulations. We also introduce several improvements to the Atomic Cluster Expansion module. Building on these advances, we train our models on OMat24, sAlex, and MPTrj, and introduce TECE-OAM-RRA-1.0, which achieve state-of-the-art (SOTA) performance on the Matbench Discovery.

stat.ML↗

arXiv2026

A Cartesian-3j Framework for Machine Learning Interatomic Potentials

Machine learning interatomic potentials (MLIPs) have brought substantial gains in the extrapolation capability in computational chemistry. However, most equivariant models are typically built with spherical tensors (STs), while Cartesian tensor formulations remain less developed despite their natural alignment with atomic coordinates and tensorial targets. In this work, we develop a Cartesian framework for irreducible Cartesian tensors (ICTs) by introduce the \texttt{Cartesian-3j} symbol and Cartesian Generalized Clebsch-Gordan Coefficients, which serve as direct analogues of the \texttt{Wigner-3j} symbol and Generalized Clebsch-Gordan coefficients defined for ST coupling. We extend the \texttt{e3nn} library to support ICT product, and use this framework to build Cartesian counterparts of \texttt{MACE}, \texttt{NequIP}, and \texttt{Allegro}, allowing the first controlled comparison where architectures are held fixed and only the tensor basis is changed. Our experiments show that irreducible Cartesian models can achieve accuracy comparable to spherical counterparts, but direct Cartesianization incurs unfavorable compute and memory scaling, motivating dedicated Cartesian architectural choices. Leveraging ICTs and our framework, we introduce \texttt{TACE-v1-OAM-M} and demonstrate that it achieves competitive performance on Matbench Discovery compared to state-of-the-art ST models.

physics.chem-ph↗

arXiv2026

Spectral/Spatial Tensor Atomic Cluster Expansion with Universal Embeddings in Cartesian Space

Equivariant atomistic machine learning models have largely been built on spherical-tensor representations, where explicit angular-momentum coupling introduces substantial complexity and systematic extensions beyond energies and forces remain challenging, often requires problem-specific architectural choices. Here we introduce the Tensor Atomic Cluster Expansion (TACE), which unifies scalar and tensorial modeling in Cartesian and space by decomposing local environments into irreducible Cartesian tensors (ICT) constructing a controlled many-body hierarchy with atomic cluster expansion (ACE). In addition to performing ACE in the frequency domain, we propose an efficient Clebsch-Gordan-free alternative in the spatial domain. TACE provides universal invariant (e.g., fidelity tags and charges) and equivariant (e.g., external electric fields and non-collinear magnetic moments) embeddings and predicted tensorial observables are handled on equal footing and enabling explicit control at inference. We demonstrate the accuracy, stability, and efficiency across finite molecules and extended materials, including in-domain and out-of-domain benchmarks, spectra, Hessian, external-field responses, charged systems, and multi-fidelity/head training. We further show its robustness on nonequilibrium/reactive datasets and controlled scaling when extending to large foundation model datasets.

stat.ML↗

arXiv2025

Identifying discreditable firms in a large-scale ownership network

Violations of laws and regulations about food safety, production safety, quality standard and environmental protection, or negative consequences from loan, guarantee and pledge contracts, may result in operating and credit risks of firms. The above illegal or trust-breaking activities are collectively called discreditable activities, and firms with discreditable activities are named as discreditable firms. Identification of discreditable firms is of great significance for investment attraction, bank lending, equity investment, supplier selection, job seeking, and so on. In this paper, we collect registration records of about 113 million Chinese firms and construct an ownership network with about 6 million nodes, where each node is a firm who has invested at least one firm or has been invested by at least one firm. Analysis of publicly available records of discreditable activities show strong network effect, namely the probability of a firm to be discreditable is remarkably higher than the average probability given the fact that one of its investors or investees is discreditable. In comparison, for the risk of being a discreditable firm, an investee has higher impact than an investor in average. The impact of a firm on surrounding firms decays along with the increasing topological distance, analogous to the well-known "three degrees of separation" phenomenon. The uncovered correlation of discreditable activities can be considered as a representative example of network effect, in addition to the propagation of diseases, opinions and human behaviors. Lastly, we show that the utilization of the network effect largely improves the accuracy of the algorithm to identify discreditable firms.

cs.CY↗

arXiv2024

Quantum Shadow Gradient Descent for Variational Quantum Algorithms

Gradient-based optimizers have been proposed for training variational quantum circuits in settings such as quantum neural networks (QNNs). The task of gradient estimation, however, has proven to be challenging, primarily due to distinctive quantum features such as state collapse and measurement incompatibility. Conventional techniques, such as the parameter-shift rule, necessitate several fresh samples in each iteration to estimate the gradient due to the stochastic nature of state measurement. Owing to state collapse from measurement, the inability to reuse samples in subsequent iterations motivates a crucial inquiry into whether fundamentally more efficient approaches to sample utilization exist. In this paper, we affirm the feasibility of such efficiency enhancements through a novel procedure called quantum shadow gradient descent (QSGD), which uses a single sample per iteration to estimate all components of the gradient. Our approach is based on an adaptation of shadow tomography that significantly enhances sample efficiency. Through detailed theoretical analysis, we show that QSGD has a significantly faster convergence rate than existing methods under locality conditions. We present detailed numerical experiments supporting all of our theoretical claims.

quant-ph↗

arXiv2024

Break the Chain: Large Language Models Can be Shortcut Reasoners

Recent advancements in Chain-of-Thought (CoT) reasoning utilize complex modules but are hampered by high token consumption, limited applicability, and challenges in reproducibility. This paper conducts a critical evaluation of CoT prompting, extending beyond arithmetic to include complex logical and commonsense reasoning tasks, areas where standard CoT methods fall short. We propose the integration of human-like heuristics and shortcuts into language models (LMs) through "break the chain" strategies. These strategies disrupt traditional CoT processes using controlled variables to assess their efficacy. Additionally, we develop innovative zero-shot prompting strategies that encourage the use of shortcuts, enabling LMs to quickly exploit reasoning clues and bypass detailed procedural steps. Our comprehensive experiments across various LMs, both commercial and open-source, reveal that LMs maintain effective performance with "break the chain" strategies. We also introduce ShortcutQA, a dataset specifically designed to evaluate reasoning through shortcuts, compiled from competitive tests optimized for heuristic reasoning tasks such as forward/backward reasoning and simplification. Our analysis confirms that ShortcutQA not only poses a robust challenge to LMs but also serves as an essential benchmark for enhancing reasoning efficiency in AI.

cs.CL↗

arXiv2021

Simple Contrastive Representation Adversarial Learning for NLP Tasks

Self-supervised learning approach like contrastive learning is attached great attention in natural language processing. It uses pairs of training data augmentations to build a classification task for an encoder with well representation ability. However, the construction of learning pairs over contrastive learning is much harder in NLP tasks. Previous works generate word-level changes to form pairs, but small transforms may cause notable changes on the meaning of sentences as the discrete and sparse nature of natural language. In this paper, adversarial training is performed to generate challenging and harder learning adversarial examples over the embedding space of NLP as learning pairs. Using contrastive learning improves the generalization ability of adversarial training because contrastive loss can uniform the sample distribution. And at the same time, adversarial training also enhances the robustness of contrastive learning. Two novel frameworks, supervised contrastive adversarial learning (SCAL) and unsupervised SCAL (USCAL), are proposed, which yields learning pairs by utilizing the adversarial training for contrastive learning. The label-based loss of supervised tasks is exploited to generate adversarial examples while unsupervised tasks bring contrastive loss. To validate the effectiveness of the proposed framework, we employ it to Transformer-based models for natural language understanding, sentence semantic textual similarity and adversarial learning tasks. Experimental results on GLUE benchmark tasks show that our fine-tuned supervised method outperforms BERT$_{base}$ over 1.75\%. We also evaluate our unsupervised method on semantic textual similarity (STS) tasks, and our method gets 77.29\% with BERT$_{base}$. The robustness of our approach conducts state-of-the-art results under multiple adversarial datasets on NLI tasks.

cs.CL↗

arXiv2019

Thermal conductivity and local thermodynamic equilibrium of stochastic energy exchange models

In this paper we study macroscopic thermodynamic properties of a stochastic microscopic heat conduction model that is reduced from deterministic problems. Our goal is to numerically check how the `low energy site effect' inherited from the deterministic model would affect the macroscopic thermodynamic properties such as the thermal conductivity and the local thermodynamic equilibrium. After a series of numerical computations, our conclusion is that neither the thermal conductivity nor the existence of local thermodynamic equilibrium is qualitatively changed by this effect.

math-ph↗