arXiv subjects

Tao Yang

Publications and source records attributed to Tao Yang.

At least 217 records · Page 12Linked to original sources

arXiv2023

FARA: Future-aware Ranking Algorithm for Fairness Optimization

Ranking systems are the key components of modern Information Retrieval (IR) applications, such as search engines and recommender systems. Besides the ranking relevance to users, the exposure fairness to item providers has also been considered an important factor in ranking optimization. Many fair ranking algorithms have been proposed to jointly optimize both ranking relevance and fairness. However, we find that most existing fair ranking methods adopt greedy algorithms that only optimize rankings for the next immediate session or request. As shown in this paper, such a myopic paradigm could limit the upper bound of ranking optimization and lead to suboptimal performance in the long term. To this end, we propose \textbf{FARA}, a novel \textbf{F}uture-\textbf{A}ware \textbf{R}anking \textbf{A}lgorithm for ranking relevance and fairness optimization. Instead of greedily optimizing rankings for the next immediate session, FARA plans ahead by jointly optimizing multiple ranklists together and saving them for future sessions. Specifically, FARA first uses the Taylor expansion to investigate how future ranklists will influence the overall fairness of the system. Then, based on the analysis of the Taylor expansion, FARA adopts a two-phase optimization algorithm where we first solve an optimal future exposure planning problem and then construct the optimal ranklists according to the optimal future exposure planning. Theoretically, we show that FARA is optimal for ranking relevance and fairness joint optimization. Empirically, our extensive experiments on three semi-synthesized datasets show that FARA is efficient, effective, and can deliver significantly better ranking performance compared to state-of-the-art fair ranking methods. We make our implementation public at \href{https://github.com/Taosheng-ty/QP_fairness/}{https://github.com/Taosheng-ty/QP\_fairness/}.

cs.IR↗

arXiv2023

Inferior Alveolar Nerve Segmentation in CBCT images using Connectivity-Based Selective Re-training

Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important step in many dental and maxillofacial surgery applications to prevent irreversible damage to the nerve during the procedure.The ToothFairy2023 Challenge aims to establish a 3D maxillofacial dataset consisting of all sparse labels and partial dense labels, and improve the ability of automatic IAN segmentation. In this work, in order to avoid the negative impact brought by sparse labeling, we transform the mixed supervised problem into a semi-supervised problem. Inspired by self-training via pseudo labeling, we propose a selective re-training framework based on IAN connectivity. Our method is quantitatively evaluated on the ToothFairy verification cases, achieving the dice similarity coefficient (DSC) of 0.7956, and 95\% hausdorff distance (HD95) of 4.4905, and wining the champion in the competition. Code is available at https://github.com/GaryNico517/SSL-IAN-Retraining.

cs.CV↗

arXiv2023

Structure and dynamics of binary Bose-Einstein condensates with vortex phase imprinting

The combination of multi-component Bose-Einstein condensates (BECs) and phase imprinting techniques provides an ideal platform for exploring nonlinear dynamics and investigating the quantum transport properties of superfluids. In this paper, we study abundant density structures and corresponding dynamics of phase-separated binary Bose-Einstein condensates with phase-imprinted single vortex or vortex dipole. By adjusting the ratio between the interspecies and intraspecies interactions, and the locations of the phase singularities, the typical density profiles such as ball-shell structures, crescent-gibbous structures, Matryoshka-like structures, sector-sector structures and sandwich-type structures appear, and the phase diagrams are obtained. The dynamics of these structures exhibit diverse properties, including the penetration of vortex dipoles, emergence of half-vortex dipoles, co-rotation of sectors, and oscillation between sectors. The pinning effects induced by a potential defect are also discussed, which is useful for controlling and manipulating individual quantum states.

cond-mat.quant-gas↗

arXiv2023

Ore Extension of Group-cograded Hopf Coquasigroups

The aim of this paper is the Ore extension of group-cograded Hopf coquasigroups. This paper first shows a categorical interpretation and some examples of group-cograded Hopf coquasigroups, and then gives a necessary and sufficient conditions for the Ore extensions of group-cograded Hopf coquasigroups to be group-cograded Hopf coquasigroups. Finally, a certain isomorphism between Ore extensions are considered.

math.RA↗

arXiv2023

Representation Sparsification with Hybrid Thresholding for Fast SPLADE-based Document Retrieval

Learned sparse document representations using a transformer-based neural model has been found to be attractive in both relevance effectiveness and time efficiency. This paper describes a representation sparsification scheme based on hard and soft thresholding with an inverted index approximation for faster SPLADE-based document retrieval. It provides analytical and experimental results on the impact of this learnable hybrid thresholding scheme.

cs.IR↗

arXiv2023

Design and simulation of a novel 4H-SiC LGAD timing device

Silicon-based fast time detectors have been widely used in high energy physics, nuclear physics, space exploration and other fields in recent years. However, silicon detectors often require complex low-temperature systems when operating in irradiation environment, and their detection performance decrease with the increase of irradiation dose. Compared with silicon, silicon carbide (SiC) has a wider bandgap, higher atomic displacement energy, saturated electron drift velocity and thermal conductivity. Simultaneously, the low gain avalanche detector avoids crosstalk and high noise from high multiplication due to its moderate gain, and thus can maintain a high detector signal without increasing noise. Thus, the 4H-SiC particle detector, especially the low gain avalanche detector has the potential to detect the minimal ionized particles (MIPs) under extreme irradiation and high temperature environments. In this work, the emphasis was placed on the design of a 4H-SiC Low Gain Avalanche Detector (LGAD), especially the epitaxial structure and technical process which played the main roles. In addition, a simulation tool--RASER(RAdiation SEmiconductoR) was developed to simulate the performances including the electrical properties and time resolution of the 4H-SiC LGAD we proposed. The working voltage and gain effectiveness of the LGAD were verified by the simulation of electrical performances. The time resolution of the LGAD is (35.0 $\pm$ 0.2) ps under the electrical field of -800 V, which is better than that of the 4H-SiC PIN detector.

physics.ins-det↗

arXiv2023

Distributed Online Convex Optimization with Adversarial Constraints: Reduced Cumulative Constraint Violation Bounds under Slater's Condition

This paper considers distributed online convex optimization with adversarial constraints. In this setting, a network of agents makes decisions at each round, and then only a portion of the loss function and a coordinate block of the constraint function are privately revealed to each agent. The loss and constraint functions are convex and can vary arbitrarily across rounds. The agents collaborate to minimize network regret and cumulative constraint violation. A novel distributed online algorithm is proposed and it achieves an $\mathcal{O}(T^{\max\{c,1-c\}})$ network regret bound and an $\mathcal{O}(T^{1-c/2})$ network cumulative constraint violation bound, where $T$ is the number of rounds and $c\in(0,1)$ is a user-defined trade-off parameter. When Slater's condition holds (i.e, there is a point that strictly satisfies the inequality constraints), the network cumulative constraint violation bound is reduced to $\mathcal{O}(T^{1-c})$. Moreover, if the loss functions are strongly convex, then the network regret bound is reduced to $\mathcal{O}(\log(T))$, and the network cumulative constraint violation bound is reduced to $\mathcal{O}(\sqrt{\log(T)T})$ and $\mathcal{O}(\log(T))$ without and with Slater's condition, respectively. To the best of our knowledge, this paper is the first to achieve reduced (network) cumulative constraint violation bounds for (distributed) online convex optimization with adversarial constraints under Slater's condition. Finally, the theoretical results are verified through numerical simulations.

math.OC↗

arXiv2023

Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity

Lesion segmentation of ultrasound medical images based on deep learning techniques is a widely used method for diagnosing diseases. Although there is a large amount of ultrasound image data in medical centers and other places, labeled ultrasound datasets are a scarce resource, and it is likely that no datasets are available for new tissues/organs. Transfer learning provides the possibility to solve this problem, but there are too many features in natural images that are not related to the target domain. As a source domain, redundant features that are not conducive to the task will be extracted. Migration between ultrasound images can avoid this problem, but there are few types of public datasets, and it is difficult to find sufficiently similar source domains. Compared with natural images, ultrasound images have less information, and there are fewer transferable features between different ultrasound images, which may cause negative transfer. To this end, a multi-source adversarial transfer learning network for ultrasound image segmentation is proposed. Specifically, to address the lack of annotations, the idea of adversarial transfer learning is used to adaptively extract common features between a certain pair of source and target domains, which provides the possibility to utilize unlabeled ultrasound data. To alleviate the lack of knowledge in a single source domain, multi-source transfer learning is adopted to fuse knowledge from multiple source domains. In order to ensure the effectiveness of the fusion and maximize the use of precious data, a multi-source domain independent strategy is also proposed to improve the estimation of the target domain data distribution, which further increases the learning ability of the multi-source adversarial migration learning network in multiple domains.

eess.IV↗

arXiv2023

Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization

Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental abilities for humans to support rapid knowledge learning and generalize to new tasks, with which the deep learning models struggle. Towards human-like intelligence, various works on disentangled representation learning have been proposed, and recently some studies on compositional generalization have been presented. However, few works study the relationship between disentanglement and compositional generalization, and the observed results are inconsistent. In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization. This insight also resonates the neuroscience research that the brain encodes information in neuron population activity rather than individual neurons. Motivated by this observation, we further propose a method to reform the scalar-based disentanglement works ($β$-TCVAE and FactorVAE) to be vector-based to increase both capabilities. We investigate the impact of the dimensions of vector-based representation and one important question: whether better disentanglement indicates higher compositional generalization. In summary, our study demonstrates that it is possible to achieve both good concept recognition and novel concept composition, contributing an important step towards human-like intelligence.

cs.CV↗

arXiv2023

Mitigating Exploitation Bias in Learning to Rank with an Uncertainty-aware Empirical Bayes Approach

Ranking is at the core of many artificial intelligence (AI) applications, including search engines, recommender systems, etc. Modern ranking systems are often constructed with learning-to-rank (LTR) models built from user behavior signals. While previous studies have demonstrated the effectiveness of using user behavior signals (e.g., clicks) as both features and labels of LTR algorithms, we argue that existing LTR algorithms that indiscriminately treat behavior and non-behavior signals in input features could lead to suboptimal performance in practice. Particularly because user behavior signals often have strong correlations with the ranking objective and can only be collected on items that have already been shown to users, directly using behavior signals in LTR could create an exploitation bias that hurts the system performance in the long run. To address the exploitation bias, we propose EBRank, an empirical Bayes-based uncertainty-aware ranking algorithm. Specifically, to overcome exploitation bias brought by behavior features in ranking models, EBRank uses a sole non-behavior feature based prior model to get a prior estimation of relevance. In the dynamic training and serving of ranking systems, EBRank uses the observed user behaviors to update posterior relevance estimation instead of concatenating behaviors as features in ranking models. Besides, EBRank additionally applies an uncertainty-aware exploration strategy to explore actively, collect user behaviors for empirical Bayesian modeling and improve ranking performance. Experiments on three public datasets show that EBRank is effective, practical and significantly outperforms state-of-the-art ranking algorithms.

cs.IR↗

arXiv2023

Clustering-Aware Negative Sampling for Unsupervised Sentence Representation

Contrastive learning has been widely studied in sentence representation learning. However, earlier works mainly focus on the construction of positive examples, while in-batch samples are often simply treated as negative examples. This approach overlooks the importance of selecting appropriate negative examples, potentially leading to a scarcity of hard negatives and the inclusion of false negatives. To address these issues, we propose ClusterNS (Clustering-aware Negative Sampling), a novel method that incorporates cluster information into contrastive learning for unsupervised sentence representation learning. We apply a modified K-means clustering algorithm to supply hard negatives and recognize in-batch false negatives during training, aiming to solve the two issues in one unified framework. Experiments on semantic textual similarity (STS) tasks demonstrate that our proposed ClusterNS compares favorably with baselines in unsupervised sentence representation learning. Our code has been made publicly available.

cs.CL↗

arXiv2023

Optimizing Guided Traversal for Fast Learned Sparse Retrieval

Recent studies show that BM25-driven dynamic index skipping can greatly accelerate MaxScore-based document retrieval based on the learned sparse representation derived by DeepImpact. This paper investigates the effectiveness of such a traversal guidance strategy during top k retrieval when using other models such as SPLADE and uniCOIL, and finds that unconstrained BM25-driven skipping could have a visible relevance degradation when the BM25 model is not well aligned with a learned weight model or when retrieval depth k is small. This paper generalizes the previous work and optimizes the BM25 guided index traversal with a two-level pruning control scheme and model alignment for fast retrieval using a sparse representation. Although there can be a cost of increased latency, the proposed scheme is much faster than the original MaxScore method without BM25 guidance while retaining the relevance effectiveness. This paper analyzes the competitiveness of this two-level pruning scheme, and evaluates its tradeoff in ranking relevance and time efficiency when searching several test datasets.

cs.IR↗

arXiv2023

A geometry-aware deep network for depth estimation in monocular endoscopy

Monocular depth estimation is critical for endoscopists to perform spatial perception and 3D navigation of surgical sites. However, most of the existing methods ignore the important geometric structural consistency, which inevitably leads to performance degradation and distortion of 3D reconstruction. To address this issue, we introduce a gradient loss to penalize edge fluctuations ambiguous around stepped edge structures and a normal loss to explicitly express the sensitivity to frequently small structures, and propose a geometric consistency loss to spreads the spatial information across the sample grids to constrain the global geometric anatomy structures. In addition, we develop a synthetic RGB-Depth dataset that captures the anatomical structures under reflections and illumination variations. The proposed method is extensively validated across different datasets and clinical images and achieves mean RMSE values of 0.066 (stomach), 0.029 (small intestine), and 0.139 (colon) on the EndoSLAM dataset. The generalizability of the proposed method achieves mean RMSE values of 12.604 (T1-L1), 9.930 (T2-L2), and 13.893 (T3-L3) on the ColonDepth dataset. The experimental results show that our method exceeds previous state-of-the-art competitors and generates more consistent depth maps and reasonable anatomical structures. The quality of intraoperative 3D structure perception from endoscopic videos of the proposed method meets the accuracy requirements of video-CT registration algorithms for endoscopic navigation. The dataset and the source code will be available at https://github.com/YYM-SIA/LINGMI-MR.

cs.CV↗

arXiv2023

Spectrum of the transfer matrices of the spin chains associated with the $A^{(2)}_3$ Lie algebra

We study the exact solution of quantum integrable system associated with the $A^{(2)}_3$ twist Lie algebra, where the boundary reflection matrices have non-diagonal elements thus the $U(1)$ symmetry is broken. With the help of the fusion technique, we obtain the closed recursive relations of the fused transfer matrices. Based on them, together with the asymptotic behaviors and the values at special points, we obtain the eigenvalues and Bethe ansatz equations of the system. We also show that the method is universal and valid for the periodic boundary condition where the $U(1)$ symmetry is reserved. The results in this paper can be applied to studying the exact solution of the $A^{(2)}_n$-related integrable models with arbitrary $n$.

math-ph↗

arXiv2023

Dynamically observing the spectra of quantum droplets in optical lattice

Optical lattice plays an important role on stability and dynamics of quantum droplets. In this letter, we investigate the Bogoliubov excitation spectrum of quantum droplets in optical lattice in the thermodynamic limit. We classify the collective excitations as synchronous modes, Bloch phononic modes, and site-density imbalanced modes. For synchronous modes, we measure the dipole oscillation frequencies by quench dynamics with a sudden shift of the optical lattice, and the breathing frequencies by Floquet dynamics with a periodic change of the lattice depth. Bloch phononic modes are observable from the Landau critical velocity of the droplets. We further discuss the instability induced by the site-dependent density fluctuations, and calculate the critical filling of atoms where the growth of lattice vacancy breaks down the translational symmetry of the system. This work makes essential steps towards measuring the excitation spectrum and understanding the superfluid nature of quantum droplets in optical lattice.

cond-mat.quant-gas↗

arXiv2023

Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection

Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis. One of the challenges of this task is assembling information from various posts into an overall profile for each user. While many previous solutions simply concatenate the posts into a long document and then encode the document by sequential or hierarchical models, they introduce unwarranted orders for the posts, which may mislead the models. In this paper, we propose a dynamic deep graph convolutional network (D-DGCN) to overcome the above limitation. Specifically, we design a learn-to-connect approach that adopts a dynamic multi-hop structure instead of a deterministic structure, and combine it with a DGCN module to automatically learn the connections between posts. The modules of post encoder, learn-to-connect, and DGCN are jointly trained in an end-to-end manner. Experimental results on the Kaggle and Pandora datasets show the superior performance of D-DGCN to state-of-the-art baselines. Our code is available at https://github.com/djz233/D-DGCN.

cs.CL↗

arXiv2023

Dynamical Behaviors of Small-scale Buoyant Diffusion Flame Oscillators in Externally Swirling Flows

Small-scale flickering buoyant diffusion flames in externally swirling flows were computationally investigated with a particular interest in identifying and characterizing various distinct dynamical behaviors of the flame oscillators under different swirling flow conditions. By varying the external swirl, six distinct flame dynamical modes, such as the flickering flame, the oscillating flame, the steady flame, the lifted flame, the spiral flame, and the flame with a vortex bubble, were computationally identified in both physical and phase spaces and analyzed from the perspective of vortex dynamics. Specifically, the frequency of buoyancy-induced flame flicker nonlinearly increases with the swirling intensity in the weak swirl regime. Further increasing the swirling intensity causes the vortex shedding to occur either around the flame tip or downstream of the flame, and the flame stops flickering but oscillates with small amplitude or stays in a steady state. A sufficiently high swirling intensity locally extinguishes the flame at its base, leading to a lifted flame. In addition, the spiral mode and the vortex-bubble mode were found for the flame at large swirl angles. Through establishing the phase portrait for featuring the flow in flames, the dynamical behaviors are presented and compared in phase space.

physics.flu-dyn↗

arXiv2023

Continuous Indeterminate Probability Neural Network

This paper introduces a general model called CIPNN - Continuous Indeterminate Probability Neural Network, and this model is based on IPNN, which is used for discrete latent random variables. Currently, posterior of continuous latent variables is regarded as intractable, with the new theory proposed by IPNN this problem can be solved. Our contributions are Four-fold. First, we derive the analytical solution of the posterior calculation of continuous latent random variables and propose a general classification model (CIPNN). Second, we propose a general auto-encoder called CIPAE - Continuous Indeterminate Probability Auto-Encoder, the decoder part is not a neural network and uses a fully probabilistic inference model for the first time. Third, we propose a new method to visualize the latent random variables, we use one of N dimensional latent variables as a decoder to reconstruct the input image, which can work even for classification tasks, in this way, we can see what each latent variable has learned. Fourth, IPNN has shown great classification capability, CIPNN has pushed this classification capability to infinity. Theoretical advantages are reflected in experimental results.

cs.LG↗