arXiv subjects

Yan Yang

Publications and source records attributed to Yan Yang.

At least 91 records · Page 5Linked to original sources

arXiv2024

Identifying Research Hotspots and Future Development Trends in Current Psychology: A Bibliometric Analysis of the Past Decade's Publications

By conducting a bibliometric analysis on 4,869 publications in Current Psychology from 2013 to 2022, this paper examined the annual publications and annual citations, as well as the leading institutions, countries, and keywords. CiteSpace, VOSviewer and SCImago Graphica were utilized for visualization analysis. On one hand, this paper analyzed the academic influence of Current Psychology over the past decade. On the other hand, it explored the research hotspots and future development trends within the field of international psychology. The results revealed that the three main research areas covered in the publications of Current Psychology were: the psychological well-being of young people, the negative emotions of adults, and self-awareness and management. The latest research hotspots highlighted in the journal include negative emotions, personality, and mental health. The three main development trends of Current Psychology are: 1) exploring the personality psychology of both adolescents and adults, 2) promoting the interdisciplinary research to study social psychological issues through the use of diversified research methods, and 3) emphasizing the emotional psychology of individuals and their interaction with social reality, from a people-oriented perspective.

cs.DL↗

arXiv2024

Towards Alleviating Text-to-Image Retrieval Hallucination for CLIP in Zero-shot Learning

Pretrained cross-modal models, for instance, the most representative CLIP, have recently led to a boom in using pre-trained models for cross-modal zero-shot tasks, considering the generalization properties. However, we analytically discover that CLIP suffers from the text-to-image retrieval hallucination, adversely limiting its capabilities under zero-shot learning: CLIP would select the image with the highest score when asked to figure out which image perfectly matches one given query text among several candidate images even though CLIP knows contents in the image. Accordingly, we propose a Balanced Score with Auxiliary Prompts (BSAP) to mitigate the CLIP's text-to-image retrieval hallucination under zero-shot learning. Specifically, we first design auxiliary prompts to provide multiple reference outcomes for every single image retrieval, then the outcomes derived from each retrieved image in conjunction with the target text are normalized to obtain the final similarity, which alleviates hallucinations in the model. Additionally, we can merge CLIP's original results and BSAP to obtain a more robust hybrid outcome (BSAP-H). Extensive experiments on two typical zero-shot learning tasks, i.e., Referring Expression Comprehension (REC) and Referring Image Segmentation (RIS), are conducted to demonstrate the effectiveness of our BSAP. Specifically, when evaluated on the validation dataset of RefCOCO in REC, BSAP increases CLIP's performance by 20.6%. Further, we validate that our strategy could be applied in other types of pretrained cross-modal models, such as ALBEF and BLIP.

cs.MM↗

arXiv2024

A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4

Dialogue state tracking (DST) is evaluated by exact matching methods, which rely on large amounts of labeled data and ignore semantic consistency, leading to over-evaluation. Currently, leveraging large language models (LLM) in evaluating natural language processing tasks has achieved promising results. However, using LLM for DST evaluation is still under explored. In this paper, we propose a two-dimensional zero-shot evaluation method for DST using GPT-4, which divides the evaluation into two dimensions: accuracy and completeness. Furthermore, we also design two manual reasoning paths in prompting to further improve the accuracy of evaluation. Experimental results show that our method achieves better performance compared to the baselines, and is consistent with traditional exact matching based methods.

cs.CL↗

arXiv2024

Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentation

Data augmentation methods have been a promising direction to improve the performance of small models for low-resource dialogue state tracking. However, traditional methods rely on pre-defined user goals and neglect the importance of data complexity in this task. In this paper, we propose EDZ-DA, an Easy-to-Difficult Zero-shot Data Augmentation framework for low-resource dialogue state tracking that utilizes large language models to automatically catch the relationships of different domains and then generate the dialogue data. We also complicate the dialogues based on the domain relation to enhance the model's capability for co-reference slot tracking. Furthermore, we permute slot values to mitigate the influence of output orders and the problem of incomplete value generation. Experimental results illustrate the superiority of our proposed method compared to previous strong data augmentation baselines on MultiWOZ.

cs.CL↗

arXiv2024

Counterexamples to two conjectures on mean color numbers of graphs

The mean color number of an $n$-vertex graph $G$, denoted by $μ(G)$, is the average number of colors used in all proper $n$-colorings of $G$. For any graph $G$ and a vertex $w$ in $G$, Dong (2003) conjectured that if $H$ is a graph obtained from a graph $G$ by deleting all but one of the edges which are incident to $w$, then $μ(G)\geq μ(H)$; and also conjectured that $μ(G)\geq μ((G-w)\cup K_1)$. We prove that there is an infinite family of counterexamples to these two conjectures.

math.CO↗

arXiv2024

Adversarial Reweighting with $α$-Power Maximization for Domain Adaptation

The practical Domain Adaptation (DA) tasks, e.g., Partial DA (PDA), open-set DA, universal DA, and test-time adaptation, have gained increasing attention in the machine learning community. In this paper, we propose a novel approach, dubbed Adversarial Reweighting with $α$-Power Maximization (ARPM), for PDA where the source domain contains private classes absent in target domain. In ARPM, we propose a novel adversarial reweighting model that adversarially learns to reweight source domain data to identify source-private class samples by assigning smaller weights to them, for mitigating potential negative transfer. Based on the adversarial reweighting, we train the transferable recognition model on the reweighted source distribution to be able to classify common class data. To reduce the prediction uncertainty of the recognition model on the target domain for PDA, we present an $α$-power maximization mechanism in ARPM, which enriches the family of losses for reducing the prediction uncertainty for PDA. Extensive experimental results on five PDA benchmarks, i.e., Office-31, Office-Home, VisDA-2017, ImageNet-Caltech, and DomainNet, show that our method is superior to recent PDA methods. Ablation studies also confirm the effectiveness of components in our approach. To theoretically analyze our method, we deduce an upper bound of target domain expected error for PDA, which is approximately minimized in our approach. We further extend ARPM to open-set DA, universal DA, and test time adaptation, and verify the usefulness through experiments.

cs.CV↗

arXiv2024

Bounds for DP color function and canonical labelings

The DP-coloring is a generalization of the list coloring, introduced by Dvořák and Postle. Let $\mathcal{H}=(L,H)$ be a cover of a graph $G$ and $P_{DP}(G,\mathcal{H})$ be the number of $\mathcal{H}$-colorings of $G$. The DP color function $P_{DP}(G,m)$ of $G$, introduced by Kaul and Mudrock, is the minimum value of $P_{DP}(G,\mathcal{H})$ where the minimum is taken over all possible $m$-fold covers $\mathcal{H}$ of $G$. For the family of $n$-vertex connected graphs, one can deduce that trees maximize the DP color function, from two results of Kaul and Mudrock. In this paper we obtain tight upper bounds for the DP color function of $n$-vertex $2$-connected graphs. Another concern in this paper is the canonical labeling in a cover. It is well known that if an $m$-fold cover $\mathcal{H}$ of a graph $G$ has a canonical labeling, then $P_{DP}(G,\mathcal{H})=P(G,m)$ in which $P(G,m)$ is the chromatic polynomial of $G$. However the converse statement of this conclusion is not always true. We give examples that for some $m$ and $G$, there exists an $m$-fold cover $\mathcal{H}$ of $G$ such that $P_{DP}(G,\mathcal{H})=P(G,m)$, but $\mathcal{H}$ has no canonical labelings. We also prove that when $G$ is a unicyclic graph or a theta graph, for each $m\geq 3$, if $P_{DP}(G,\mathcal{H})=P(G,m)$, then $\mathcal{H}$ has a canonical labeling.

math.CO↗

arXiv2024

Anisotropy of Density Fluctuations in the Solar Wind at 1 au

A well-known property of solar wind plasma turbulence is the observed anisotropy of the autocorrelations, or equivalently the spectra, of velocity and magnetic field fluctuations. Here we explore the related but apparently not well-studied issue of the anisotropy of plasma density fluctuations in the energy-containing and inertial ranges of solar wind turbulence. Using 10 years (1998-2008) of in situ data from the Advanced Composition Explorer (ACE) mission, we find that for all but the fastest wind category, the density correlation scale is slightly larger in directions quasi-parallel to the large-scale mean magnetic field as compared to quasi-perpendicular directions. The correlation scale in fast wind is consistent with isotropic. The anisotropy as a function of the level of correlation is also explored. We find at small correlation levels, i.e., at energy-containing scales and larger, the density fluctuations are close to isotropy for fast wind, and slightly favor more rapid decorrelation in perpendicular directions for slow and medium winds. At relatively smaller (inertial range) scales where the correlation values are larger, the sense of anisotropy is reversed in all speed ranges, implying a more "slab-like" structure, especially prominent in the fast wind samples. We contrast this finding with published results on velocity and magnetic field correlations.

physics.space-ph↗

arXiv2024

Scale Separation Effects on Simulations of Plasma Turbulence

Understanding plasma turbulence requires a synthesis of experiments, observations, theory, and simulations. In the case of kinetic plasmas such as the solar wind, the lack of collisions renders the fluid closures such as viscosity meaningless and one needs to resort to higher order fluid models or kinetic models. Typically, the computational expense in such models is managed by simulating artificial values of certain parameters such as the ratio of the Alfvén speed to the speed of light ($v_A/c$) or the relative mass ratio of ions and electrons ($m_i/m_e$). Although, typically care is taken to use values as close as possible to realistic values within the computational constraints, these artificial values could potentially introduce unphysical effects. These unphysical effects could be significant at sub-ion scales, where kinetic effects are the most important. In this paper, we use the ten-moment fluid model in the Gkeyll framework to perform controlled numerical experiments, systematically varying the ion-electron mass ratio from a small value down to the realistic proton-electron mass ratio. We show that the unphysical mass ratio has a significant effect on the kinetic range dynamics as well as the heating of both the plasma species. The dissipative process for both ions and electrons become more compressive in nature, although the ions remain nearly incompressible in all cases. The electrons move from being dominated by incompressive viscous like heating/dissipation, to very compressive heating/dissipation dominated by compressions/rarefactions. While the heating change is significant for the electrons, a mass ratio of $m_i/m_e \sim 250$ captures the asymptotic behaviour of electron heating.

physics.plasm-ph↗

arXiv2024

Trustworthy Multimodal Fusion for Sentiment Analysis in Ordinal Sentiment Space

Multimodal video sentiment analysis aims to integrate multiple modal information to analyze the opinions and attitudes of speakers. Most previous work focuses on exploring the semantic interactions of intra- and inter-modality. However, these works ignore the reliability of multimodality, i.e., modalities tend to contain noise, semantic ambiguity, missing modalities, etc. In addition, previous multimodal approaches treat different modalities equally, largely ignoring their different contributions. Furthermore, existing multimodal sentiment analysis methods directly regress sentiment scores without considering ordinal relationships within sentiment categories, with limited performance. To address the aforementioned problems, we propose a trustworthy multimodal sentiment ordinal network (TMSON) to improve performance in sentiment analysis. Specifically, we first devise a unimodal feature extractor for each modality to obtain modality-specific features. Then, an uncertainty distribution estimation network is customized, which estimates the unimodal uncertainty distributions. Next, Bayesian fusion is performed on the learned unimodal distributions to obtain multimodal distributions for sentiment prediction. Finally, an ordinal-aware sentiment space is constructed, where ordinal regression is used to constrain the multimodal distributions. Our proposed TMSON outperforms baselines on multimodal sentiment analysis tasks, and empirical results demonstrate that TMSON is capable of reducing uncertainty to obtain more robust predictions.

cs.CV↗

arXiv2024

A programmable topological photonic chip

Controlling topological phases of light has allowed experimental observations of abundant topological phenomena and development of robust photonic devices. The prospect of more sophisticated controls with topological photonic devices for practical implementations requires high-level programmability. Here, we demonstrate a fully programmable topological photonic chip with large-scale integration of silicon photonic nanocircuits and microresonators. Photonic artificial atoms and their interactions in our compound system can be individually addressed and controlled, therefore allowing arbitrary altering of structural parameters and geometrical configurations for the observations of dynamic topological phase transitions and diverse photonic topological insulators. By individually programming artificial atoms on the generic chip, it has allowed comprehensive statistic characterisations of topological robustness against relatively weak disorders, as well as counterintuitive topological Anderson phase transitions induced by strong disorders. Our generic topological photonic chip that can be rapidly reprogrammed to implement multifunctionalities, prototypes a flexible and versatile platform for possible applications across fundamental science and topological technologies.

physics.optics↗

arXiv2024

Blockage-Aware Robust Beamforming in RIS-Aided Mobile Millimeter Wave MIMO Systems

Millimeter wave (mmWave) communications are sensitive to blockage over radio propagation paths. The emerging paradigm of reconfigurable intelligent surface (RIS) has the potential to overcome this issue by its ability to arbitrarily reflect the incident signals toward desired directions. This paper proposes a Neyman-Pearson (NP) criterion-based blockage-aware algorithm to improve communication resilience against blockage in mobile mmWave multiple input multiple output (MIMO) systems. By virtue of this pragmatic blockage-aware technique, we further propose an outage-constrained beamforming design for downlink mmWave MIMO transmission to achieve outage probability minimization and achievable rate maximization. To minimize the outage probability, a robust RIS beamformer with variant beamwidth is designed to combat uncertain channel state information (CSI). For the rate maximization problem, an accelerated projected gradient descent (PGD) algorithm is developed to solve the computational challenge of high-dimensional RIS phase-shift matrix (PSM) optimization. Particularly, we leverage a subspace constraint to reduce the scope of the projection operation and formulate a new Nesterov momentum acceleration scheme to speed up the convergence process of PGD. Extensive experiments confirm the effectiveness of the proposed blockage-aware approach, and the proposed accelerated PGD algorithm outperforms a number of representative baseline algorithms in terms of the achievable rate.

eess.SP↗

arXiv2024

State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Tracking

Recently, low-resource dialogue state tracking (DST) has received increasing attention. First obtaining state values then based on values to generate slot types has made great progress in this task. However, obtaining state values is still an under-studied problem. Existing extraction-based approaches cannot capture values that require the understanding of context and are not generalizable either. To address these issues, we propose a novel State VAlue Generation based framework (SVAG), decomposing DST into state value generation and domain slot generation. Specifically, we propose to generate state values and use self-training to further improve state value generation. Moreover, we design an estimator aiming at detecting incomplete generation and incorrect generation for pseudo-labeled data selection during self-training. Experimental results on the MultiWOZ 2.1 dataset show that our method which has only less than 1 billion parameters achieves state-of-the-art performance under the data ratio settings of 5%, 10%, and 25% when limited to models under 100 billion parameters. Compared to models with more than 100 billion parameters, SVAG still reaches competitive results.

cs.CL↗

arXiv2024

Spatial Transcriptomics Analysis of Zero-shot Gene Expression Prediction

Spatial transcriptomics (ST) captures gene expression within distinct regions (i.e., windows) of a tissue slide. Traditional supervised learning frameworks applied to model ST are constrained to predicting expression from slide image windows for gene types seen during training, failing to generalize to unseen gene types. To overcome this limitation, we propose a semantic guided network (SGN), a pioneering zero-shot framework for predicting gene expression from slide image windows. Considering a gene type can be described by functionality and phenotype, we dynamically embed a gene type to a vector per its functionality and phenotype, and employ this vector to project slide image windows to gene expression in feature space, unleashing zero-shot expression prediction for unseen gene types. The gene type functionality and phenotype are queried with a carefully designed prompt from a pre-trained large language model (LLM). On standard benchmark datasets, we demonstrate competitive zero-shot performance compared to past state-of-the-art supervised learning approaches.

cs.CV↗

arXiv2023

Language-driven All-in-one Adverse Weather Removal

All-in-one (AiO) frameworks restore various adverse weather degradations with a single set of networks jointly. To handle various weather conditions, an AiO framework is expected to adaptively learn weather-specific knowledge for different degradations and shared knowledge for common patterns. However, existing methods: 1) rely on extra supervision signals, which are usually unknown in real-world applications; 2) employ fixed network structures, which restrict the diversity of weather-specific knowledge. In this paper, we propose a Language-driven Restoration framework (LDR) to alleviate the aforementioned issues. First, we leverage the power of pre-trained vision-language (PVL) models to enrich the diversity of weather-specific knowledge by reasoning about the occurrence, type, and severity of degradation, generating description-based degradation priors. Then, with the guidance of degradation prior, we sparsely select restoration experts from a candidate list dynamically based on a Mixture-of-Experts (MoE) structure. This enables us to adaptively learn the weather-specific and shared knowledge to handle various weather conditions (e.g., unknown or mixed weather). Experiments on extensive restoration scenarios show our superior performance (see Fig. 1). The source code will be made available.

cs.CV↗

arXiv2023

Mapping EEG Signals to Visual Stimuli: A Deep Learning Approach to Match vs. Mismatch Classification

Existing approaches to modeling associations between visual stimuli and brain responses are facing difficulties in handling between-subject variance and model generalization. Inspired by the recent progress in modeling speech-brain response, we propose in this work a "match-vs-mismatch" deep learning model to classify whether a video clip induces excitatory responses in recorded EEG signals and learn associations between the visual content and corresponding neural recordings. Using an exclusive experimental dataset, we demonstrate that the proposed model is able to achieve the highest accuracy on unseen subjects as compared to other baseline models. Furthermore, we analyze the inter-subject noise using a subject-level silhouette score in the embedding space and show that the developed model is able to mitigate inter-subject noise and significantly reduce the silhouette score. Moreover, we examine the Grad-CAM activation score and show that the brain regions associated with language processing contribute most to the model predictions, followed by regions associated with visual processing. These results have the potential to facilitate the development of neural recording-based video reconstruction and its related applications.

cs.CV↗

arXiv2023

LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network

Recovering sharp images from dual-pixel (DP) pairs with disparity-dependent blur is a challenging task.~Existing blur map-based deblurring methods have demonstrated promising results. In this paper, we propose, to the best of our knowledge, the first framework that introduces the contrastive language-image pre-training framework (CLIP) to accurately estimate the blur map from a DP pair unsupervisedly. To achieve this, we first carefully design text prompts to enable CLIP to understand blur-related geometric prior knowledge from the DP pair. Then, we propose a format to input a stereo DP pair to CLIP without any fine-tuning, despite the fact that CLIP is pre-trained on monocular images. Given the estimated blur map, we introduce a blur-prior attention block, a blur-weighting loss, and a blur-aware loss to recover the all-in-focus image. Our method achieves state-of-the-art performance in extensive experiments (see Fig.~\ref{fig:teaser}).

cs.CV↗

arXiv2023

Debunking Free Fusion Myth: Online Multi-view Anomaly Detection with Disentangled Product-of-Experts Modeling

Multi-view or even multi-modal data is appealing yet challenging for real-world applications. Detecting anomalies in multi-view data is a prominent recent research topic. However, most of the existing methods 1) are only suitable for two views or type-specific anomalies, 2) suffer from the issue of fusion disentanglement, and 3) do not support online detection after model deployment. To address these challenges, our main ideas in this paper are three-fold: multi-view learning, disentangled representation learning, and generative model. To this end, we propose dPoE, a novel multi-view variational autoencoder model that involves (1) a Product-of-Experts (PoE) layer in tackling multi-view data, (2) a Total Correction (TC) discriminator in disentangling view-common and view-specific representations, and (3) a joint loss function in wrapping up all components. In addition, we devise theoretical information bounds to control both view-common and view-specific representations. Extensive experiments on six real-world datasets markedly demonstrate that the proposed dPoE outperforms baselines.

cs.LG↗