Search arXiv⌕ Search

arXiv subjects

Yi Liu

Publications and source records attributed to Yi Liu.

At least 541 records · Page 30Linked to original sources
arXiv2023

Knowledge Enhancement for Contrastive Multi-Behavior Recommendation

A well-designed recommender system can accurately capture the attributes of users and items, reflecting the unique preferences of individuals. Traditional recommendation techniques usually focus on modeling the singular type of behaviors between users and items. However, in many practical recommendation scenarios (e.g., social media, e-commerce), there exist multi-typed interactive behaviors in user-item relationships, such as click, tag-as-favorite, and purchase in online shopping platforms. Thus, how to make full use of multi-behavior information for recommendation is of great importance to the existing system, which presents challenges in two aspects that need to be explored: (1) Utilizing users' personalized preferences to capture multi-behavioral dependencies; (2) Dealing with the insufficient recommendation caused by sparse supervision signal for target behavior. In this work, we propose a Knowledge Enhancement Multi-Behavior Contrastive Learning Recommendation (KMCLR) framework, including two Contrastive Learning tasks and three functional modules to tackle the above challenges, respectively. In particular, we design the multi-behavior learning module to extract users' personalized behavior information for user-embedding enhancement, and utilize knowledge graph in the knowledge enhancement module to derive more robust knowledge-aware representations for items. In addition, in the optimization stage, we model the coarse-grained commonalities and the fine-grained differences between multi-behavior of users to further improve the recommendation effect. Extensive experiments and ablation tests on the three real-world datasets indicate our KMCLR outperforms various state-of-the-art recommendation methods and verify the effectiveness of our method.

cs.IR↗
arXiv2023

Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks

To address the problem of medical image recognition, computer vision techniques like convolutional neural networks (CNN) are frequently used. Recently, 3D CNN-based models dominate the field of magnetic resonance image (MRI) analytics. Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification? Our work suggests that advanced video techniques benefit MRI classification. In this paper, four datasets of Alzheimer's and Parkinson's disease recognition are utilized in experiments, together with three alternative video recognition models and data augmentation techniques that are frequently applied to video tasks. In terms of efficiency, the results reveal that the video framework performs better than 3D-CNN models by 5% - 11% with 50% - 66% less trainable parameters. This report pushes forward the potential fusion of 3D medical imaging and video understanding research.

cs.CV↗
arXiv2023

XFL: A High Performace, Lightweighted Federated Learning Framework

This paper introduces XFL, an industrial-grade federated learning project. XFL supports training AI models collaboratively on multiple devices, while utilizes homomorphic encryption, differential privacy, secure multi-party computation and other security technologies ensuring no leakage of data. XFL provides an abundant algorithms library, integrating a large number of pre-built, secure and outstanding federated learning algorithms, covering both the horizontally and vertically federated learning scenarios. Numerical experiments have shown the prominent performace of these algorithms. XFL builds a concise configuration interfaces with presettings for all federation algorithms, and supports the rapid deployment via docker containers.Therefore, we believe XFL is the most user-friendly and easy-to-develop federated learning framework. XFL is open-sourced, and both the code and documents are available at https://github.com/paritybit-ai/XFL.

cs.LG↗
arXiv2023

Characterizing Commodity Serverless Computing Platforms

Serverless computing has become a new trending paradigm in cloud computing, allowing developers to focus on the development of core application logic and rapidly construct the prototype via the composition of independent functions. With the development and prosperity of serverless computing, major cloud vendors have successively rolled out their commodity serverless computing platforms. However, the characteristics of these platforms have not been systematically studied. Measuring these characteristics can help developers to select the most adequate serverless computing platform and develop their serverless-based applications in the right way. To fill this knowledge gap, we present a comprehensive study on characterizing mainstream commodity serverless computing platforms, including AWS Lambda, Google Cloud Functions, Azure Functions, and Alibaba Cloud Function Compute. Specifically, we conduct both qualitative analysis and quantitative analysis. In qualitative analysis, we compare these platforms from three aspects (i.e., development, deployment, and runtime) based on their official documentation to construct a taxonomy of characteristics. In quantitative analysis, we analyze the runtime performance of these platforms from multiple dimensions with well-designed benchmarks. First, we analyze three key factors that can influence the startup latency of serverless-based applications. Second, we compare the resource efficiency of different platforms with 16 representative benchmarks. Finally, we measure their performance difference when dealing with different concurrent requests, and explore the potential causes in a black-box fashion. Based on the results of both qualitative and quantitative analysis, we derive a series of findings and provide insightful implications for both developers and cloud vendors.

cs.SE↗
arXiv2023

FaaSLight: General Application-Level Cold-Start Latency Optimization for Function-as-a-Service in Serverless Computing

Serverless computing is a popular cloud computing paradigm that frees developers from server management. Function-as-a-Service (FaaS) is the most popular implementation of serverless computing, representing applications as event-driven and stateless functions. However, existing studies report that functions of FaaS applications severely suffer from cold-start latency. In this paper, we propose an approach namely FaaSLight to accelerating the cold start for FaaS applications through application-level optimization. We first conduct a measurement study to investigate the possible root cause of the cold start problem of FaaS. The result shows that application code loading latency is a significant overhead. Therefore, loading only indispensable code from FaaS applications can be an adequate solution. Based on this insight, we identify code related to application functionalities by constructing the function-level call graph, and separate other code (i.e., optional code) from FaaS applications. The separated optional code can be loaded on demand to avoid the inaccurate identification of indispensable code causing application failure. In particular, a key principle guiding the design of FaaSLight is inherently general, i.e., platform- and language-agnostic. The evaluation results on real-world FaaS applications show that FaaSLight can significantly reduce the code loading latency (up to 78.95%, 28.78% on average), thereby reducing the cold-start latency. As a result, the total response latency of functions can be decreased by up to 42.05% (19.21% on average). Compared with the state-of-the-art, FaaSLight achieves a 21.25X improvement in reducing the average total response latency.

cs.DC↗
arXiv2023

EGC2: Enhanced Graph Classification with Easy Graph Compression

Graph classification is crucial in network analyses. Networks face potential security threats, such as adversarial attacks. Some defense methods may trade off the algorithm complexity for robustness, such as adversarial training, whereas others may trade off clean example performance, such as smoothingbased defense. Most suffer from high complexity or low transferability. To address this problem, we proposed EGC2, an enhanced graph classification model with easy graph compression. EGC2 captures the relationship between the features of different nodes by constructing feature graphs and improving the aggregation of the node-level representations. To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness. Experiments on ten benchmark datasets demonstrate that the proposed feature read-out and graph compression mechanisms enhance the robustness of multiple basic models, resulting in a state-of-the-art performance in terms of accuracy and robustness against various adversarial attacks.

cs.LG↗
arXiv2023

Three-dimensional sedimentation patterns of two interacting disks in a viscous fluid

The sedimentation of two spherical solid objects in a viscous fluid has been extensively investigated and well understood. However, a pair of flat disks (in three dimensions) settling in the fluid shows more complex hydrodynamic behaviors. The present work aims to improve understanding of this phenomenon by performing Direct Numerical Simulations (DNS) and physical experiments. The present results show that the sedimentation processes are significantly influenced by disk shape, characterized by a dimensionless moment of inertia I*, and Reynolds number of the leading disk Re. For the flatter disks with smaller I*, steady falling with enduring contact transits to periodic swinging with intermittent contacts as Re increases. The disks with larger I* tend to fall in a Drafting-Kissing-Tumbling (DKT) mode at low Re and to remain separated at high Re. Based on I* and Re, a phase diagram is created to classify the two-disk falling into ten distinctive patterns. The planar motion or three-dimensional motion of the disks is determined primarily by Re. Turbulent disturbance flows at a high Re contribute to the chaotic three-dimensional rotation of the disks. The chance for the two disks to contact is increased when I* and Re are reduced.

physics.flu-dyn↗
arXiv2023

Structured air lasing of N2+

Structured light has attracted great interest in scientific and technical fields. Here, we demonstrate the first generation of structured air lasing in N2+ driven by 800 nm femtosecond laser pulses. By focusing a vortex pump beam at 800 nm in N2 gas, we generate a vortex superfluorescent radiation of N2+ at 391 nm, which carries the same photon orbital angular momentum as the pump beam. With the injection of a Gaussian seed beam at 391 nm, the coherent radiation is amplified, but the vorticity is unchanged. A new physical mechanism is revealed in the vortex N2+ superfluorescent radiation: the vortex pump beam transfers the spatial spiral phase into the N2+ gain medium, and the Gaussian seed beam picks up the spatial spiral phase and is then amplified into a vortex beam. Moreover, when we employ a pump beam with a cylindrical vector mode, the Gaussian seed beam is correspondingly amplified into a cylindrical vector beam. Surprisingly, the spatial polarization state of the amplified radiation is identical to that of the vector pump beam regardless of whether the Gaussian seed beam is linearly, elliptically, or circularly polarized. Solving three-dimensional coupled wave equations, we show how a Gaussian beam becomes a cylindrical vector beam in a cylindrically symmetric gain medium. This study provides a novel approach to generating structured light via N2+ air lasing.

physics.optics↗
arXiv2022

Orbital hybridization-driven charge density wave transition in CsV3Sb5 kagome superconductor

Owing to its inherent non-trivial geometry, the unique structural motif of the recently discovered Kagome topological superconductor AV3Sb5 is an ideal host of diverse topologically non-trivial phenomena, including giant anomalous Hall conductivity, topological charge order, charge density wave, and unconventional superconductivity. Despite possessing a normal-state CDW order in the form of topological chiral charge order and diverse superconducting gaps structures, it remains unclear how fundamental atomic-level properties and many-body effects including Fermi surface nesting, electron-phonon coupling, and orbital hybridization contribute to these symmetry-breaking phenomena. Here, we report the direct participation of the V3d-Sb5p orbital hybridization in mediating the CDW phase transition in CsV3Sb5. The combination of temperature-dependent X-ray absorption and first principles studies clearly indicate the Inverse Star of David structure as the preferred reconstruction in the low-temperature CDW phase. Our results highlight the critical role that Sb orbitals plays and establish orbital hybridization as the direct mediator of the CDW states and structural transition dynamics in Kagome unconventional superconductors. This is a significant step towards the fundamental understanding and control of the emerging correlated phases from the Kagome lattice through the orbital interactions and provide promising approaches to novel regimes in unconventional orders and topology.

cond-mat.supr-con↗
arXiv2022

InternVideo: General Video Foundation Models via Generative and Discriminative Learning

The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for dynamic and complex video-level understanding tasks. To fill the gap, we present general video foundation models, InternVideo, by taking advantage of both generative and discriminative self-supervised video learning. Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications. Without bells and whistles, InternVideo achieves state-of-the-art performance on 39 video datasets from extensive tasks including video action recognition/detection, video-language alignment, and open-world video applications. Especially, our methods can obtain 91.1% and 77.2% top-1 accuracy on the challenging Kinetics-400 and Something-Something V2 benchmarks, respectively. All of these results effectively show the generality of our InternVideo for video understanding. The code will be released at https://github.com/OpenGVLab/InternVideo .

cs.CV↗
arXiv2022

Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning

Network pruning is a promising way to generate light but accurate models and enable their deployment on resource-limited edge devices. However, the current state-of-the-art assumes that the effective sub-network and the other superfluous parameters in the given network share the same distribution, where pruning inevitably involves a distribution truncation operation. They usually eliminate values near zero. While simple, it may not be the most appropriate method, as effective models may naturally have many small values associated with them. Removing near-zero values already embedded in model space may significantly reduce model accuracy. Another line of work has proposed to assign discrete prior over all possible sub-structures that still rely on human-crafted prior hypotheses. Worse still, existing methods use regularized point estimates, namely Hard Pruning, that can not provide error estimations and fail reliability justification for the pruned networks. In this paper, we propose a novel distribution-lossless pruning method, named DLLP, to theoretically find the pruned lottery within Bayesian treatment. Specifically, DLLP remodels the vanilla networks as discrete priors for the latent pruned model and the other redundancy. More importantly, DLLP uses Stein Variational Inference to approach the latent prior and effectively bypasses calculating KL divergence with unknown distribution. Extensive experiments based on small Cifar-10 and large-scaled ImageNet demonstrate that our method can obtain sparser networks with great generalization performance while providing quantified reliability for the pruned model.

cs.CV↗
arXiv2022

Spherical Message Passing for 3D Graph Networks

We consider representation learning of 3D molecular graphs in which each atom is associated with a spatial position in 3D. This is an under-explored area of research, and a principled message passing framework is currently lacking. In this work, we conduct analyses in the spherical coordinate system (SCS) for the complete identification of 3D graph structures. Based on such observations, we propose the spherical message passing (SMP) as a novel and powerful scheme for 3D molecular learning. SMP dramatically reduces training complexity, enabling it to perform efficiently on large-scale molecules. In addition, SMP is capable of distinguishing almost all molecular structures, and the uncovered cases may not exist in practice. Based on meaningful physically-based representations of 3D information, we further propose the SphereNet for 3D molecular learning. Experimental results demonstrate that the use of meaningful 3D information in SphereNet leads to significant performance improvements in prediction tasks. Our results also demonstrate the advantages of SphereNet in terms of capability, efficiency, and scalability. Our code is publicly available as part of the DIG library (https://github.com/divelab/DIG).

cs.LG↗
arXiv2022

Measuring neutrino dynamics in NMSSM with a right-handed sneutrino LSP at the ILC

We study the possibility of measuring neutrino Yukawa couplings in the Next-to-Minimal Supersymmetric Standard Model with right-handed neutrinos (NMSSMr) when the lightest Supersymmetric partner (a right-handed sneutrino) is the Dark Matter (DM) candidate, by exploiting a `dijet + dilepton + Missing Transverse Energy' (MET) signature. We show that, unlike the miminal realisation of Supersymmetry (SUSY), i.e., the MSSM, for which the DM candidate is a much heavier (fermionic) state (a neutralino), this non-minimal SUSY model offers one with a much lighter (bosonic) state (a sneutrino) as DM, which can be produced at future $e^+e^-$ colliders with energies up to about 500 GeV. The emerging signal, from chargino pair production and subsequent decay, is extremely pure so it allows for the possibility of extracting the Yukawa parameters of the (s)neutrino sector. These results should then motivate searches for light DM signals at such accelerators, where a DM candidate with mass at the Electro-Weak (EW) scale can then be accessed.

hep-ph↗
arXiv2022

Realization of Practical Eightfold Fermions and Fourfold van Hove Singularity in TaCo$_2$Te$_2$

Space groups describing the symmetry of lattice structure allow the emergence of fermionic quasiparticles with various degeneracy in the band structure. Theoretical efforts have predicted many materials hosting fermions with the highest degeneracy, i.e., eightfold fermions, yet lacking experimental realization. Here, we explore the band degeneracies in TaCo$_2$Te$_2$ crystals. Through systematic experimental and theoretical analyses, we establish TaCo$_2$Te$_2$ as a nonsymmorphic crystal with negligible spin-orbit coupling (SOC) and long-range magnetic order. These critical properties guarantee the first realization of practical eightfold fermions and fourfold van Hove singularity, as directly observed by photoemission spectroscopy. TaCo$_2$Te$_2$ serves as a topological quantum critical platform, which can be tuned into various magnetic, topologically trivial, and nontrivial phases by adding strain, magnetic field, or SOC. The latter is demonstrated by our first-principles calculations, which show that enhancing SOC in TaCo$_2$Te$_2$ will promote the experimental observation of bulk hourglass fermions. Our results establish TaCo$_2$Te$_2$ as a unique platform to explore states of matter intertwining magnetism, correlation, symmetry, and band topology.

cond-mat.str-el↗
arXiv2022

The activated scaling behavior of quantum Griffiths singularity in two-dimensional superconductors

Quantum Griffiths singularity is characterized by the divergence of the dynamical critical exponent with the activated scaling law and has been widely observed in various two-dimensional superconductors. Recently, the direct activated scaling analysis with the irrelevant correction has been proposed and successfully used to analyze the experimental data of crystalline PdTe2 and polycrystalline \b{eta}-W films, which provides new evidence of quantum Griffiths singularity. Here we show that the direct activated scaling analysis is applicable to the experimental data in different superconducting films, including tri-layer Ga films and LaAlO3/SrTiO3 interface superconductor. When taking the irrelevant correction into account, we calculate the corrected sheet resistance at ultralow temperatures. The scaling behavior of the corrected resistance in a comparably large temperature regime and the theoretical fitting of the phase boundary give unambiguous evidence of quantum Griffiths singularity. Compared to the previous method based on the finite size scaling, the direct activated scaling analysis represents a more direct and precise way to analyze the experimental data of quantum Griffiths singularity in diverse two-dimensional superconductors.

cond-mat.supr-con↗
arXiv2022

Token-level Speaker Change Detection Using Speaker Difference and Speech Content via Continuous Integrate-and-fire

In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to segment the audio and then transcribe each segmentation. These two stages are addressed separately by speaker change detection (SCD) and automatic speech recognition (ASR). Most previous SCD systems rely solely on speaker information and ignore the importance of speech content. In this paper, we propose a novel SCD system that considers both cues of speaker difference and speech content. These two cues are converted into token-level representations by the continuous integrate-and-fire (CIF) mechanism and then combined for detecting speaker changes on the token acoustic boundaries. We evaluate the performance of our approach on a public real-recorded meeting dataset, AISHELL-4. The experiment results show that our method outperforms a competitive frame-level baseline system by 2.45% equal coverage-purity (ECP). In addition, we demonstrate the importance of speech content and speaker difference to the SCD task, and the advantages of conducting SCD on the token acoustic boundaries compared with conducting SCD frame by frame.

cs.SD↗
arXiv2022

InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges

In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, including Moment Queries, Natural Language Queries, Future Hand Prediction, State Change Object Detection, and Short-term Object Interaction Anticipation. InternVideo-Ego4D is an effective paradigm to adapt the strong foundation model to the downstream ego-centric video understanding tasks with simple head designs. In these five tasks, the performance of InternVideo-Ego4D comprehensively surpasses the baseline methods and the champions of CVPR2022, demonstrating the powerful representation ability of InternVideo as a video foundation model. Our code will be released at https://github.com/OpenGVLab/ego4d-eccv2022-solutions

cs.CV↗
arXiv2022

Foveated Rendering: a State-of-the-Art Survey

Recently, virtual reality (VR) technology has been widely used in medical, military, manufacturing, entertainment, and other fields. These applications must simulate different complex material surfaces, various dynamic objects, and complex physical phenomena, increasing the complexity of VR scenes. Current computing devices cannot efficiently render these complex scenes in real time, and delayed rendering makes the content observed by the user inconsistent with the user's interaction, causing discomfort. Foveated rendering is a promising technique that can accelerate rendering. It takes advantage of human eyes' inherent features and renders different regions with different qualities without sacrificing perceived visual quality. Foveated rendering research has a history of 31 years and is mainly focused on solving the following three problems. The first is to apply perceptual models of the human visual system into foveated rendering. The second is to render the image with different qualities according to foveation principles. The third is to integrate foveated rendering into existing rendering paradigms to improve rendering performance. In this survey, we review foveated rendering research from 1990 to 2021. We first revisit the visual perceptual models related to foveated rendering. Subsequently, we propose a new foveated rendering taxonomy and then classify and review the research on this basis. Finally, we discuss potential opportunities and open questions in the foveated rendering field. We anticipate that this survey will provide new researchers with a high-level overview of the state of the art in this field, furnish experts with up-to-date information and offer ideas alongside a framework to VR display software and hardware designers and engineers.

cs.GR↗