arXiv subjects

Haiyang Yang

Publications and source records attributed to Haiyang Yang.

17 recordsLinked to original sources

arXiv2025

GSID: Generative Semantic Indexing for E-Commerce Product Understanding

Structured representation of product information is a major bottleneck for the efficiency of e-commerce platforms, especially in second-hand ecommerce platforms. Currently, most product information are organized based on manually curated product categories and attributes, which often fail to adequately cover long-tail products and do not align well with buyer preference. To address these problems, we propose \textbf{G}enerative \textbf{S}emantic \textbf{I}n\textbf{D}exings (GSID), a data-driven approach to generate product structured representations. GSID consists of two key components: (1) Pre-training on unstructured product metadata to learn in-domain semantic embeddings, and (2) Generating more effective semantic codes tailored for downstream product-centric applications. Extensive experiments are conducted to validate the effectiveness of GSID, and it has been successfully deployed on the real-world e-commerce platform, achieving promising results on product understanding and other downstream tasks.

cs.IR↗

arXiv2025

Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification

Identifying attribute values from product profiles is a key task for improving product search, recommendation, and business analytics on e-commerce platforms, which we called Product Attribute Value Identification (PAVI) . However, existing PAVI methods face critical challenges, such as cascading errors, inability to handle out-of-distribution (OOD) attribute values, and lack of generalization capability. To address these limitations, we introduce Multi-Value-Product Retrieval-Augmented Generation (MVP-RAG), combining the strengths of retrieval, generation, and classification paradigms. MVP-RAG defines PAVI as a retrieval-generation task, where the product title description serves as the query, and products and attribute values act as the corpus. It first retrieves similar products of the same category and candidate attribute values, and then generates the standardized attribute values. The key advantages of this work are: (1) the proposal of a multi-level retrieval scheme, with products and attribute values as distinct hierarchical levels in PAVI domain (2) attribute value generation of large language model to significantly alleviate the OOD problem and (3) its successful deployment in a real-world industrial environment. Extensive experimental results demonstrate that MVP-RAG performs better than the state-of-the-art baselines.

cs.IR↗

arXiv2025

TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms. However, existing PAVI methods face critical challenges, such as inferring implicit values, handling out-of-distribution (OOD) values, and producing normalized outputs. To address these limitations, we introduce Taxonomy-Aware Contrastive Learning Retrieval (TACLR), the first retrieval-based method for PAVI. TACLR formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity. It leverages contrastive training with taxonomy-aware hard negative sampling and employs adaptive inference with dynamic thresholds. TACLR offers three key advantages: (1) it effectively handles implicit and OOD values while producing normalized outputs; (2) it scales to thousands of categories, tens of thousands of attributes, and millions of values; and (3) it supports efficient inference for high-load industrial deployment. Extensive experiments on proprietary and public datasets validate the effectiveness and efficiency of TACLR. Further, it has been successfully deployed on the real-world e-commerce platform Xianyu, processing millions of product listings daily with frequently updated, large-scale attribute taxonomies. We release the code to facilitate reproducibility and future research at https://github.com/SuYindu/TACLR.

cs.CL↗

arXiv2023

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the metaverse. It is desirable to have a general pretrain model for versatile human-centric downstream tasks. This paper forges ahead along this path from the aspects of both benchmark and pretraining methods. Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting. To learn both coarse-grained and fine-grained knowledge in human bodies, we further propose a \textbf{P}rojector \textbf{A}ssis\textbf{T}ed \textbf{H}ierarchical pretraining method (\textbf{PATH}) to learn diverse knowledge at different granularity levels. Comprehensive evaluations on HumanBench show that our PATH achieves new state-of-the-art results on 17 downstream datasets and on-par results on the other 2 datasets. The code will be publicly at \href{https://github.com/OpenGVLab/HumanBench}{https://github.com/OpenGVLab/HumanBench}.

cs.CV↗

arXiv2023

Saliency Guided Contrastive Learning on Scene Images

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations from less-curated scene images is essential for pushing self-supervised learning to a higher level. Different from curated images which include simple and clear semantic information, scene images are more complex and mosaic because they often include complex scenes and multiple objects. Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images. In this work, we leverage the saliency map derived from the model's output during learning to highlight these discriminative regions and guide the whole contrastive learning. Specifically, the saliency map first guides the method to crop its discriminative regions as positive pairs and then reweighs the contrastive losses among different crops by its saliency scores. Our method significantly improves the performance of self-supervised learning on scene images by +1.1, +4.3, +2.2 Top1 accuracy in ImageNet linear evaluation, Semi-supervised learning with 1% and 10% ImageNet labels, respectively. We hope our insights on saliency maps can motivate future research on more general-purpose unsupervised representation learning from scene data.

cs.CV↗

arXiv2023

Pressure-induced nontrivial $Z_2$ band topology and superconductivity in transition metal chalcogenide $\mathrm{Ta}_2 \mathrm{Ni}_3 \mathrm{Te}_5$

The unique electronic and crystal structures driven by external pressure in transition metal chalcogenides (TMCs) can host emergent quantum states. Here we report pressure-induced metallization, nontrivial $Z_2$ band topology and superconductivity in TMC $\mathrm{Ta}_2 \mathrm{Ni}_3 \mathrm{Te}_5$. Our electrical transport measurements show that the metallization emerges at 3.3 GPa, followed by appearance of the superconductivity at $P_{\mathrm{c}}$ = 21.3 GPa with $T_{\mathrm{c}} \sim$ 0.4 K. Room-temperature synchrotron x-ray diffraction experiments demonstrate the stability of the pristine orthorhombic structure upon compression. Our first-principles calculations further reveal a topological phase transition (from $Z_2=0$ to $Z_2=1$), which occurs after $\mathrm{Ta}_2 \mathrm{Ni}_3 \mathrm{Te}_5$ is turned into an electron-hole compensated semimetal by pressure. The pressure-induced superconductivity at $P_{\mathrm{c}}$ could be attributed to the abruptly enhanced density of states at the Fermi level. These findings demonstrate that $\mathrm{Ta}_2 \mathrm{Ni}_3 \mathrm{Te}_5$ is a new platform for realizing exotic quantum phenomena in TMCs, as well as exploring the interplay between topological property and superconductivity.

cond-mat.supr-con↗

arXiv2023

Pressure-induced superconductivity in quasi-one-dimensional semimetal $\mathrm{Ta}_2 \mathrm{PdSe}_6$

Here we report the discovery of pressure-induced superconductivity in quasi-one-dimensional $\mathrm{Ta}_2 \mathrm{PdSe}_6$, through a combination of electrical transport, synchrotron x-ray diffraction, and theoretical calculations. Our transport measurements show that the superconductivity appears at a critical pressure $P_{\mathrm{c}} \sim 18.3$ GPa and is robust upon further compression up to $62.6$ GPa. The estimated upper critical field $μ_0 H_{\mathrm{c} 2}(0)$ in the pressurized $\mathrm{Ta}_2 \mathrm{PdSe}_6$ is much lower than the Pauli limiting field, in contrast to the case in its isostructural analogs $M_2 \mathrm{Pd}_{\mathrm{x}} X_5$ $(M=\mathrm{Nb}$, Ta; $X=\mathrm{S}, \mathrm{Se})$. Concomitant with the occurrence of superconductivity, anomalies in pressuredependent transport properties are observed, including sign reversal of Hall coefficient, abnormally enhanced resistance, and dramatically suppressed magnetoresistance. Meanwhile, room-temperature synchrotron x-ray diffraction experiments reveal the stability of the pristine monoclinic structure (space group $C 2 / m$ ) upon compression. Combined with the density functional theory calculations, we argue that a pressure-induced Lifshitz transition could be the electronic origin of the emergent superconductivity in $\mathrm{Ta}_2 \mathrm{PdSe}_6$.

cond-mat.supr-con↗

arXiv2022

Spatial-Temporal Graph Convolutional Gated Recurrent Network for Traffic Forecasting

As an important part of intelligent transportation systems, traffic forecasting has attracted tremendous attention from academia and industry. Despite a lot of methods being proposed for traffic forecasting, it is still difficult to model complex spatial-temporal dependency. Temporal dependency includes short-term dependency and long-term dependency, and the latter is often overlooked. Spatial dependency can be divided into two parts: distance-based spatial dependency and hidden spatial dependency. To model complex spatial-temporal dependency, we propose a novel framework for traffic forecasting, named Spatial-Temporal Graph Convolutional Gated Recurrent Network (STGCGRN). We design an attention module to capture long-term dependency by mining periodic information in traffic data. We propose a Double Graph Convolution Gated Recurrent Unit (DGCGRU) to capture spatial dependency, which integrates graph convolutional network and GRU. The graph convolution part models distance-based spatial dependency with the distance-based predefined adjacency matrix and hidden spatial dependency with the self-adaptive adjacency matrix, respectively. Specially, we employ the multi-head mechanism to capture multiple hidden dependencies. In addition, the periodic pattern of each prediction node may be different, which is often ignored, resulting in mutual interference of periodic information among nodes when modeling spatial dependency. For this, we explore the architecture of model and improve the performance. Experiments on four datasets demonstrate the superior performance of our model.

cs.LG↗

arXiv2022

Sign-reversed anomalous Nernst effect in the ferromagnetic Weyl-semimetal Fe$_{3-x}$GeTe$_2$: the role of Fe vacancies

Anomalous Nernst effect, as a thermal partner of anomalous Hall effect, is particularly sensitive to the Berry curvature anomaly near the Fermi level, and has been used to probe the topological nature of quantum materials. In this work, we report the observation of both effects in the ferromagnetic Weyl-semimetal Fe$_{3-x}$GeTe$_2$ with tunable Fe vacancies. With decreasing Fe vacancies, the anomalous Hall conductivity evolves as a function of the longitudinal conductivity from the hopping region to the region where the intrinsic Berry curvature contribution dominates. Concomitant evolutions in the anomalous Nernst signal and the anomalous off-diagonal thermoelectric coefficient are observed below the Curie temperature, displaying a unique sign change caused by the Fe vacancies. Combining these results with first-principles calculations, we argue that the Fe-vacancy concentration plays a unique role in simultaneously tuning the chemical potential and ferromagnetism, which in turn controls the Berry curvature contribution in this family of ferromagnetic topological semimetals.

cond-mat.mtrl-sci↗

arXiv2022

Domain Invariant Masked Autoencoders for Self-supervised Learning from Multi-domains

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain. Therefore, the self-supervised learning from multiple domains task is proposed to learn domain-invariant features that are not only suitable for evaluation on the same domain as the training set but also can be generalized to unseen domains. In this paper, we propose a Domain-invariant Masked AutoEncoder (DiMAE) for self-supervised learning from multi-domains, which designs a new pretext task, \emph{i.e.,} the cross-domain reconstruction task, to learn domain-invariant features. The core idea is to augment the input image with style noise from different domains and then reconstruct the image from the embedding of the augmented image, regularizing the encoder to learn domain-invariant features. To accomplish the idea, DiMAE contains two critical designs, 1) content-preserved style mix, which adds style information from other domains to input while persevering the content in a parameter-free manner, and 2) multiple domain-specific decoders, which recovers the corresponding domain style of input to the encoded domain-invariant features for reconstruction. Experiments on PACS and DomainNet illustrate that DiMAE achieves considerable gains compared with recent state-of-the-art methods.

cs.CV↗

arXiv2021

On the tensor product of two oriented quantum algebras

In this paper, we give the oriented quantum algebra (abbr. OQA) structures on the tensor product of two different OQAs by using Chen's weak $\mathfrak{R}$-matrix in [J. Algebra 204(1998):504-531]. As a special case, the OQA structures on the tensor product of an OQA with itself are provided, which are different from Radford's results in [J. Knot Theory Ramifications 16(2007):929-957].

math.RA↗

arXiv2021

Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation

Conventional unsupervised domain adaptation (UDA) methods need to access both labeled source samples and unlabeled target samples simultaneously to train the model. While in some scenarios, the source samples are not available for the target domain due to data privacy and safety. To overcome this challenge, recently, source-free domain adaptation (SFDA) has attracted the attention of researchers, where both a trained source model and unlabeled target samples are given. Existing SFDA methods either adopt a pseudo-label based strategy or generate more samples. However, these methods do not explicitly reduce the distribution shift across domains, which is the key to a good adaptation. Although there are no source samples available, fortunately, we find that some target samples are very similar to the source domain and can be used to approximate the source domain. This approximated domain is denoted as the pseudo-source domain. In this paper, inspired by this observation, we propose a novel method based on the pseudo-source domain. The proposed method firstly generates and augments the pseudo-source domain, and then employs distribution alignment with four novel losses based on pseudo-label based strategy. Among them, a domain adversarial loss is introduced between the pseudo-source domain the remaining target domain to reduce the distribution shift. The results on three real-world datasets verify the effectiveness of the proposed method.

cs.LG↗

arXiv2020

Angle-dependent magnetoresistance and its implications for Lifshitz transition in W2As3

Lifshitz transition represents a sudden reconstruction of Fermi surface structure, giving rise to anomalies in electronic properties of materials. Such a transition does not necessarily rely on symmetry-breaking and thus is topological. It holds a key to understand the origin of many exotic quantum phenomena, for example the mechanism of extremely large magnetoresistance (MR) in topological Dirac/Weyl semimetals. Here, we report studies of the angle-dependent MR (ADMR) and the thermoelectric effect in W2As3 single crystal. The compound shows a large unsaturated MR (of about 70000% at 4.2 K and 53 T). The most striking finding is that the ADMR significantly deforms from the horizontal dumbbell-like shape above 40 K to the vertical lotus-like pattern below 30 K. The window of 30-40 K also corresponds substantial changes in Hall effect, thermopower and Nernst coefficient, implying an abrupt change of Fermi surface topology. Such a temperature-induced Lifshitz transition results in a compensation of electron-hole transport and the large MR as well. We thus suggest that the similar method can be applicable in detecting a Fermi-surface change of a variety of quantum states when a direct Fermi-surface measurement is not possible.

cond-mat.mtrl-sci↗

arXiv2020

PrBi: Topology meets quadrupolar degrees of freedom

Novel materials incorporating electronic degrees of freedom other than charge, including spin, orbital or valley \textit{et al} have manifested themselves to be of the great interests and applicable potentials. Recently, the multipolar degrees of freedom have attracted remarkable attention in the electronic correlated effects. In this work, we systematically studied the transport, magnetic and thermodynamic properties of the topological semimetal candidate PrBi in the framework of crystalline electric field theory. Our results demonstrate the $Γ_3$ non-Kramers doublet as the ground state of Pr$^{3+}$ (4$f^2$) ions. This ground state is nonmagnetic but carries a non-zero quadrupolar moment $\langle\hat{O}_2^0\rangle$. A quadrupolar phase transition is inferred below 0.08 K. No obvious quadrupolar Kondo effect can be identified. Ultrahigh-field quantum oscillation measurements confirm PrBi as a semimetal with non-trivial Berry phase and low total carrier density 0.06 /f.u. We discuss the interplay between low carrier density and $4f^2$ quadrupolar moment, and ascribe the weak quadrupolar ordering and Kondo effect to consequences of the low carrier density. PrBi, thus, opens a new window to the physics of topology and strongly correlated effect with quadrupolar degrees of freedom in the low-carrier-density limit, evoking the need for a reexamination of the Nozières exhaustion problem in the context of multi-channel Kondo effect.

cond-mat.str-el↗

arXiv2019

Synthesis and physical properties of CeRu$_2$As$_2$ and CeIr$_2$As$_2$

We studied the physical properties of two Kondo-lattice compounds, CeRu$_2$As$_2$ and CeIr$_2$As$_2$, by a combination of electric transport, magnetic and thermodynamic measurements. They are of ThCr$_2$Si$_2$-type and CaBe$_2$Ge$_2$-type crystalline structures, respectively. CeRu$_2$As$_2$ shows localized long-range antiferromagnetic ordering below $T_N$=4.3 K, with a moderate electronic Sommerfeld coefficient $γ_0$=35 mJ/mol$\cdot$K$^2$. A field-induced metamagnetic transition is observed near 2 T below $T_N$. Magnetic susceptibility measurements on aligned CeRu$_2$As$_2$ powders suggest that it has an easy axis and that the cerium moments align uniaxially along $\mathbf{c}$ axis. In contrast, CeIr$_2$As$_2$ is a magnetically nonordered heavy-fermion metal with enhanced $γ_0$$>$300 mJ/mol$\cdot$K$^2$. The initial onset Kondo temperatures of the two compounds are respectively 6 K and 30 K. We discuss the role of the crystal structure to the strength of Kondo coupling. This work provides two new dense Kondo-lattice materials for further investigations on electronic correlation, quantum criticality and heavy-electron effects.

cond-mat.str-el↗

arXiv2018

Superconductivity, Electronic Phase Diagram and Pressure Effect in Sr_{1-x}Pr_{x}FBiS_{2}

Based on a combination of X-ray diffraction, electrical transports, magnetic susceptibility, specific heat and pressure effect measurements, we report a series of BiS$_{2}$-based Sr$_{1-x}$Pr$_{x}$FBiS$_{2}$ superconductors with the maximum $T_c$ of 2.7 K for $x =$ 0.5 at ambient pressure. Superconductivity can be only observed at 0.4 $\leq$ x $\leq$ 0.7 while the normal state resistivity shows the semiconducting-like behaviors. $χ(T)$ displays the low superconducting shielding volume fractions and $C(T)$ does not exhibit distinguishable anomaly around $T_c$, suggesting a filamentary superconductivity in the Pr-doped polycrystalline samples. By varying doping concentrations, an electrnoic phase diagram can thus be established. Upon applying pressure on the optimal doping Sr$_{0.5}$Pr$_{0.5}$FBiS$_{2}$ system, $T_c$ is abruptly enhanced, reaches 8.5 K at a critical pressure of $P_c =$ 1.5 GPa and remains a slight increase up to 9.7 K up to 2.5 GPa. Accompanied with the enhancement of superconductivity from the low-$T_c$ phase to the high-$T_c$ phase, the normal state undergoes a semiconductor-to-metal transition under pressure. The scenario can be linked to the enhancement of orbital overlap of Bi-6p and S-p, contributing to the bulk superconductivity above $P_c$. Phase diagram for Sr$_{0.5}$Pr$_{0.5}$FBiS$_{2}$ is also obtained.

cond-mat.supr-con↗

arXiv2018

Giant anomalous Nernst effect in the magnetic Weyl semimetal Co3Sn2S2

In ferromagnetic solids, even in absence of magnetic field, a transverse voltage can be generated by a longitudinal temperature gradient. This thermoelectric counterpart of the Anomalous Hall effect (AHE) is dubbed the Anomalous Nernst effect (ANE). Expected to scale with spontaneous magnetization, both these effects arise because of the Berry curvature at the Fermi energy. Here, we report the observation of a giant ANE in a newly-discovered magnetic Weyl semimetal Co$_3$Sn$_2$S$_2$ crystal. Hall resistivity and Nernst signal both show sharp jumps at a threshold field and exhibit a clear hysteresis loop below the ferromagnetic transition temperature. The ANE signal peaks a maximum value of about 5 miuV/K which is comparable to the largest seen in any magnetic material. Moreover, the anomalous transverse thermoelectric conductivity becomes as large as about 10 A/K.m at 70 K, the largest in known semimetals. The observed ANE signal is much larger than what is expected according to the magnetization.

cond-mat.mtrl-sci↗