arXiv subjects

Qi Li

Publications and source records attributed to Qi Li.

At least 379 records · Page 21Linked to original sources

arXiv2022

Supervised Contrastive Learning with Tree-Structured Parzen Estimator Bayesian Optimization for Imbalanced Tabular Data

Class imbalance has a detrimental effect on the predictive performance of most supervised learning algorithms as the imbalanced distribution can lead to a bias preferring the majority class. To solve this problem, we propose a Supervised Contrastive Learning (SCL) method with Tree-structured Parzen Estimator (TPE) technique for imbalanced tabular datasets. Contrastive learning (CL) can extract the information hidden in data even without labels and has shown some potential for imbalanced learning tasks. SCL further considers the label information based on CL, which also addresses the insufficient data augmentation techniques of tabular data. Therefore, in this work, we propose to use SCL to learn a discriminative representation of imbalanced tabular data. Additionally, the hyper-parameter temperature of SCL has a decisive influence on the performance and is difficult to tune. We introduce TPE, a well-known Bayesian optimization technique, to automatically select the best temperature. Experiments are conducted on both binary and multi-class imbalanced tabular datasets. As shown in the results obtained, TPE outperforms three other hyper-parameter optimization (HPO) methods such as grid search, random search, and genetic algorithm. More importantly, the proposed SCL-TPE method achieves much-improved performance compared with the state-of-the-art methods.

cs.LG↗

arXiv2022

GAN-based Facial Attribute Manipulation

Facial Attribute Manipulation (FAM) aims to aesthetically modify a given face image to render desired attributes, which has received significant attention due to its broad practical applications ranging from digital entertainment to biometric forensics. In the last decade, with the remarkable success of Generative Adversarial Networks (GANs) in synthesizing realistic images, numerous GAN-based models have been proposed to solve FAM with various problem formulation approaches and guiding information representations. This paper presents a comprehensive survey of GAN-based FAM methods with a focus on summarizing their principal motivations and technical details. The main contents of this survey include: (i) an introduction to the research background and basic concepts related to FAM, (ii) a systematic review of GAN-based FAM methods in three main categories, and (iii) an in-depth discussion of important properties of FAM methods, open issues, and future research directions. This survey not only builds a good starting point for researchers new to this field but also serves as a reference for the vision community.

cs.CV↗

arXiv2022

Boosting the convergence of low-variance DSMC by GSIS

The low-variance direct simulation Monte Carlo (LVDSMC) is a powerful method to simulate low-speed rarefied gas flows. However, in the near-continuum flow regime, due to limitations on the time step and spatial cell size, it takes plenty of time to find the steady-state solution. Here we remove these deficiencies by coupling the LVDSMC with the general synthetic iterative scheme (GSIS) which permits the simulation at the hydrodynamic scale rather than the much smaller kinetic scale. As a proof of concept, we propose the stochastic-deterministic coupling method based on the Bhatnagar-Gross-Krook kinetic model. First, macroscopic synthetic equations are derived exactly from the kinetic equation, which not only contain the Navier-Stokes-Fourier constitutive relation, but also encompass the higher-order terms describing the rarefaction effects. Then, the high-order terms are extracted from LVDSMC and fed into synthetic equations to predict macroscopic properties which are closer to the steady-state solution than LVDSMC. Finally, the state of simulation particles in LVDSMC is updated to reflect the change of macroscopic properties. As a result, the convergence to steady state is greatly accelerated, and the restriction on cell size and the time step are removed: after simulating several canonical rarefied gas flows, we demonstrate that the LVDSMC-GSIS reduces the computational cost by two orders of magnitude in the near-continuum flow regime.

physics.flu-dyn↗

arXiv2022

IdeaReader: A Machine Reading System for Understanding the Idea Flow of Scientific Publications

Understanding the origin and influence of the publication's idea is critical to conducting scientific research. However, the proliferation of scientific publications makes it difficult for researchers to sort out the evolution of all relevant literature. To this end, we present IdeaReader, a machine reading system that finds out which papers are most likely to inspire or be influenced by the target publication and summarizes the ideas of these papers in natural language. Specifically, IdeaReader first clusters the references and citations (first-order or higher-order) of the target publication, and the obtained clusters are regarded as the topics that inspire or are influenced by the target publication. It then picks out the important papers from each cluster to extract the skeleton of the idea flow. Finally, IdeaReader automatically generates a literature review of the important papers in each topic. Our system can help researchers gain insight into how scientific ideas flow from the target publication's references to citations by the automatically generated survey and the visualization of idea flow.

cs.DL↗

arXiv2022

Disentangled Graph Contrastive Learning for Review-based Recommendation

User review data is helpful in alleviating the data sparsity problem in many recommender systems. In review-based recommendation methods, review data is considered as auxiliary information that can improve the quality of learned user/item or interaction representations for the user rating prediction task. However, these methods usually model user-item interactions in a holistic manner and neglect the entanglement of the latent factors behind them, e.g., price, quality, or appearance, resulting in suboptimal representations and reducing interpretability. In this paper, we propose a Disentangled Graph Contrastive Learning framework for Review-based recommendation (DGCLR), to separately model the user-item interactions based on different latent factors through the textual review data. To this end, we first model the distributions of interactions over latent factors from both semantic information in review data and structural information in user-item graph data, forming several factor graphs. Then a factorized message passing mechanism is designed to learn disentangled user/item representations on the factor graphs, which enable us to further characterize the interactions and adaptively combine the predicted ratings from multiple factors via a devised attention mechanism. Finally, we set two factor-wise contrastive learning objectives to alleviate the sparsity issue and model the user/item and interaction features pertinent to each factor more accurately. Empirical results over five benchmark datasets validate the superiority of DGCLR over the state-of-the-art methods. Further analysis is offered to interpret the learned intent factors and rating prediction in DGCLR.

cs.IR↗

arXiv2022

On the Privacy Risks of Cell-Based NAS Architectures

Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance. Little progress has been made to systematically understand if the NAS-searched architectures are robust to privacy attacks while abundant work has already shown that human-designed architectures are prone to privacy attacks. In this paper, we fill this gap and systematically measure the privacy risks of NAS architectures. Leveraging the insights from our measurement study, we further explore the cell patterns of cell-based NAS architectures and evaluate how the cell patterns affect the privacy risks of NAS-searched architectures. Through extensive experiments, we shed light on how to design robust NAS architectures against privacy attacks, and also offer a general methodology to understand the hidden correlation between the NAS-searched architectures and other privacy risks.

cs.CR↗

arXiv2022

Kinetic modelling of rarefied gas flows with radiation

Two kinetic models are proposed for high-temperature rarefied (or non-equilibrium) gas flows with radiation. One of the models uses the Boltzmann collision operator to model the translational motion of gas molecules, which has the ability to capture the influence of intermolecular potentials, while the other adopts the relaxation time approximations, which has higher computational efficiency. In the kinetic modelling, not only the transport coefficients such as the shear/bulk viscosity and thermal conductivity but also their fundamental relaxation processes are recovered. Also, the non-equilibrium dynamics of gas flow and radiation are coupled in a self-consistent manner. The two proposed kinetic models are first validated by the direct simulation Monte Carlo method in several non-radiative rarefied gas flows, including the normal shock wave, Fourier flow, Couette flow, and the creep flow driven by the Maxwell demon. Then, the rarefied gas flows with strong radiation are investigated, not only in the above one-dimensional gas flows, but also in the two-dimensional radiative hypersonic flow passing cylinder. In addition to the Knudsen number of gas flow, the influence of the photon Knudsen number and relative radiation strength is scrutinised. It is found that the radiation can make a profound contribution to the total heat transfer on obstacle surface.

physics.flu-dyn↗

arXiv2022

Improving Distantly Supervised Relation Extraction by Natural Language Inference

To reduce human annotations for relation extraction (RE) tasks, distantly supervised approaches have been proposed, while struggling with low performance. In this work, we propose a novel DSRE-NLI framework, which considers both distant supervision from existing knowledge bases and indirect supervision from pretrained language models for other tasks. DSRE-NLI energizes an off-the-shelf natural language inference (NLI) engine with a semi-automatic relation verbalization (SARV) mechanism to provide indirect supervision and further consolidates the distant annotations to benefit multi-classification RE models. The NLI-based indirect supervision acquires only one relation verbalization template from humans as a semantically general template for each relationship, and then the template set is enriched by high-quality textual patterns automatically mined from the distantly annotated corpus. With two simple and effective data consolidation strategies, the quality of training data is substantially improved. Extensive experiments demonstrate that the proposed framework significantly improves the SOTA performance (up to 7.73\% of F1) on distantly supervised RE benchmark datasets.

cs.CL↗

arXiv2022

Adaptive Domain Interest Network for Multi-domain Recommendation

Industrial recommender systems usually hold data from multiple business scenarios and are expected to provide recommendation services for these scenarios simultaneously. In the retrieval step, the topK high-quality items selected from a large number of corpus usually need to be various for multiple scenarios. Take Alibaba display advertising system for example, not only because the behavior patterns of Taobao users are diverse, but also differentiated scenarios' bid prices assigned by advertisers vary significantly. Traditional methods either train models for each scenario separately, ignoring the cross-domain overlapping of user groups and items, or simply mix all samples and maintain a shared model which makes it difficult to capture significant diversities between scenarios. In this paper, we present Adaptive Domain Interest network that adaptively handles the commonalities and diversities across scenarios, making full use of multi-scenarios data during training. Then the proposed method is able to improve the performance of each business domain by giving various topK candidates for different scenarios during online inference. Specifically, our proposed ADI models the commonalities and diversities for different domains by shared networks and domain-specific networks, respectively. In addition, we apply the domain-specific batch normalization and design the domain interest adaptation layer for feature-level domain adaptation. A self training strategy is also incorporated to capture label-level connections across domains.ADI has been deployed in the display advertising system of Alibaba, and obtains 1.8% improvement on advertising revenue.

cs.IR↗

arXiv2022

Voice-Face Homogeneity Tells Deepfake

Detecting forgery videos is highly desirable due to the abuse of deepfake. Existing detection approaches contribute to exploring the specific artifacts in deepfake videos and fit well on certain data. However, the growing technique on these artifacts keeps challenging the robustness of traditional deepfake detectors. As a result, the development of generalizability of these approaches has reached a blockage. To address this issue, given the empirical results that the identities behind voices and faces are often mismatched in deepfake videos, and the voices and faces have homogeneity to some extent, in this paper, we propose to perform the deepfake detection from an unexplored voice-face matching view. To this end, a voice-face matching method is devised to measure the matching degree of these two. Nevertheless, training on specific deepfake datasets makes the model overfit certain traits of deepfake algorithms. We instead, advocate a method that quickly adapts to untapped forgery, with a pre-training then fine-tuning paradigm. Specifically, we first pre-train the model on a generic audio-visual dataset, followed by the fine-tuning on downstream deepfake data. We conduct extensive experiments over three widely exploited deepfake datasets - DFDC, FakeAVCeleb, and DeepfakeTIMIT. Our method obtains significant performance gains as compared to other state-of-the-art competitors. It is also worth noting that our method already achieves competitive results when fine-tuned on limited deepfake data.

cs.CV↗

arXiv2022

MOST-Net: A Memory Oriented Style Transfer Network for Face Sketch Synthesis

Face sketch synthesis has been widely used in multi-media entertainment and law enforcement. Despite the recent developments in deep neural networks, accurate and realistic face sketch synthesis is still a challenging task due to the diversity and complexity of human faces. Current image-to-image translation-based face sketch synthesis frequently encounters over-fitting problems when it comes to small-scale datasets. To tackle this problem, we present an end-to-end Memory Oriented Style Transfer Network (MOST-Net) for face sketch synthesis which can produce high-fidelity sketches with limited data. Specifically, an external self-supervised dynamic memory module is introduced to capture the domain alignment knowledge in the long term. In this way, our proposed model could obtain the domain-transfer ability by establishing the durable relationship between faces and corresponding sketches on the feature level. Furthermore, we design a novel Memory Refinement Loss (MR Loss) for feature alignment in the memory module, which enhances the accuracy of memory slots in an unsupervised manner. Extensive experiments on the CUFS and the CUFSF datasets show that our MOST-Net achieves state-of-the-art performance, especially in terms of the Structural Similarity Index(SSIM).

cs.CV↗

arXiv2022

Towards future directions in data-integrative supervised prediction of human aging-related genes

Identification of human genes involved in the aging process is critical due to the incidence of many diseases with age. A state-of-the-art approach for this purpose infers a weighted dynamic aging-specific subnetwork by mapping gene expression (GE) levels at different ages onto the protein-protein interaction network (PPIN). Then, it analyzes this subnetwork in a supervised manner by training a predictive model to learn how network topologies of known aging- vs. non-aging-related genes change across ages. Finally, it uses the trained model to predict novel aging-related genes. However, the best current subnetwork resulting from this approach still yields suboptimal prediction accuracy. This could be because it was inferred using outdated GE and PPIN data. Here, we evaluate whether analyzing a weighted dynamic aging-specific subnetwork inferred from newer GE and PPIN data improves prediction accuracy upon analyzing the best current subnetwork inferred from outdated data. Unexpectedly, we find that not to be the case. To understand this, we perform aging-related pathway and Gene Ontology (GO) term enrichment analyses. We find that the suboptimal prediction accuracy, regardless of which GE or PPIN data is used, may be caused by the current knowledge about which genes are aging-related being incomplete, or by the current methods for inferring or analyzing an aging-specific subnetwork being unable to capture all of the aging-related knowledge. These findings can potentially guide future directions towards improving supervised prediction of aging-related genes via -omics data integration.

q-bio.MN↗

arXiv2022

High-order harmonic generations in tilted Weyl semimetals

We investigate high-order harmonic generations (HHGs) under the comparison of Weyl cones in two types. Due to the hyperboloidal electron pocket structure, strong noncentrosymmetrical generations in high orders are observed around a single type-II Weyl point, especially at frequency zero. Such remarkable DC signal is proved to have attributions from the intraband transition after spectral decomposition. Under weak pulse electric field , the linear optical response of a non-tilted Weyl cone is consistent with the Kubo theory. With more numerical simulations, we conclude the non-zero chemical potential can enhance the even-order generations, from the slightly tilted system to the over-tilted systems. In consideration of dynamical symmetries, type-I and -II Weyl cones also show different selective responses under the circularly polarized light. Finally, using a more realistic model containing two pairs of Weyl points, we demonstrate the paired Weyl points with opposite chirality could suppress the overall even-order generations.

cond-mat.mes-hall↗

arXiv2022

Multiple-access relay stations for long-haul fiber-optic radio frequency transfer

We report on the realization of a long-haul radio frequency (RF) transfer scheme by using multiple-access relay stations (MARSs). The proposed scheme with independent link noise compensation for each fiber sub-link effectively solves the limitation of compensation bandwidth for long-haul transfer. The MARS can have the capability to share the same modulated optical signal for the front and rear fiber sub-links, simplifying the configuration at the repeater station and enabling the transfer system to have the multiple-access capability. At the same time, we for the first time theoretically model the effect of the MARS position on the fractional frequency instability of the fiber-optic RF transfer, demonstrating that the MARS position has little effect on system's performance when the ratio of the front and rear fiber sub-links is around $1:1$. We experimentally demonstrate a 1 GHz signal transfer by using one MARS connecting 260 and 280 km fiber links with the fractional frequency instabilities of less than $5.9\times10^{-14}$ at 1 s and $8.5\times10^{-17}$ at 10,000 s at the remote site and of $5.6\times10^{-14}$ and $6.6\times10^{-17}$ at the integration times of 1 s and 10,000 s at the MARS. The proposed scalable technique can arbitrarily add the same MARSs in the fiber link, which has great potential in realizing ultra-long-haul RF transfer.

eess.SP↗

arXiv2022

Magnetic phase transition induced ferroelectric polarization in BaFeF4 with room temperature weak ferromagnetism

BaMF4 (M=Fe, Co, Ni and Mn) family are typical multiferroic materials, having antiferromagnetism at around liquid nitrogen temperature. In this work, polycrystalline BaFeF4 has been prepared by solid state reaction. The slight deficiency of Fe leads to the coexistence of valence states of +2 and +3, facilitating the electrons to hop between the neighboring Fe2+ and Fe3+ ions through the middle F- ion, leading to the strong double exchange interaction with weak ferromagnetism above room temperature. A bifurcation at about 170 K between the zero-field-cooled and field-cooled temperature dependent magnetization curves indicates the onset of 2-dimensional antiferromagnetism, which is completed at about 125 K with the sudden drop of magnetization. Despite the fact of type-I multiferroic, its magnetoelectricity can be evidenced by the pyroelectric current, which shows a peak starting at about 170 K and finishing at about 125 K. The saturated ferroelectric polarization change of around 34 μC/m2 is observed, which is switchable by the reversed poling electric field and decreases to about 30 μC/m2 under a magnetic field of 90 kOe. This magnetoelectricity can be qualitatively reproduced by first-principles calculations. Our results represent substantial progress to search for high-temperature multiferroics in ferroelectric fluorides.

cond-mat.mtrl-sci↗

arXiv2022

IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes

Building embodied intelligent agents that can interact with 3D indoor environments has received increasing research attention in recent years. While most works focus on single-object or agent-object visual functionality and affordances, our work proposes to study a new kind of visual relationship that is also important to perceive and model -- inter-object functional relationships (e.g., a switch on the wall turns on or off the light, a remote control operates the TV). Humans often spend little or no effort to infer these relationships, even when entering a new room, by using our strong prior knowledge (e.g., we know that buttons control electrical devices) or using only a few exploratory interactions in cases of uncertainty (e.g., multiple switches and lights in the same room). In this paper, we take the first step in building AI system learning inter-object functional relationships in 3D indoor environments with key technical contributions of modeling prior knowledge by training over large-scale scenes and designing interactive policies for effectively exploring the training scenes and quickly adapting to novel test scenes. We create a new benchmark based on the AI2Thor and PartNet datasets and perform extensive experiments that prove the effectiveness of our proposed method. Results show that our model successfully learns priors and fast-interactive-adaptation strategies for exploring inter-object functional relationships in complex 3D scenes. Several ablation studies further validate the usefulness of each proposed module.

cs.CV↗

arXiv2022

GX-Plug: a Middleware for Plugging Accelerators to Distributed Graph Processing

Recently, research communities highlight the necessity of formulating a scalability continuum for large-scale graph processing, which gains the scale-out benefits from distributed graph systems, and the scale-up benefits from high-performance accelerators. To this end, we propose a middleware, called the GX-plug, for the ease of integrating the merits of both. As a middleware, the GX-plug is versatile in supporting different runtime environments, computation models, and programming models. More, for improving the middleware performance, we study a series of techniques, including pipeline shuffle, synchronization caching and skipping, and workload balancing, for intra-, inter-, and beyond-iteration optimizations, respectively. Experiments show that our middleware efficiently plugs accelerators to representative distributed graph systems, e.g., GraphX and Powergraph, with up-to 20x acceleration ratio.

cs.DC↗

arXiv2022

AnyFace: Free-style Text-to-Face Synthesis and Manipulation

Existing text-to-image synthesis methods generally are only applicable to words in the training dataset. However, human faces are so variable to be described with limited words. So this paper proposes the first free-style text-to-face method namely AnyFace enabling much wider open world applications such as metaverse, social media, cosmetics, forensics, etc. AnyFace has a novel two-stream framework for face image synthesis and manipulation given arbitrary descriptions of the human face. Specifically, one stream performs text-to-face generation and the other conducts face image reconstruction. Facial text and image features are extracted using the CLIP (Contrastive Language-Image Pre-training) encoders. And a collaborative Cross Modal Distillation (CMD) module is designed to align the linguistic and visual features across these two streams. Furthermore, a Diverse Triplet Loss (DT loss) is developed to model fine-grained features and improve facial diversity. Extensive experiments on Multi-modal CelebA-HQ and CelebAText-HQ demonstrate significant advantages of AnyFace over state-of-the-art methods. AnyFace can achieve high-quality, high-resolution, and high-diversity face synthesis and manipulation results without any constraints on the number and content of input captions.

cs.CV↗