arXiv subjects

Yifei Yang

Publications and source records attributed to Yifei Yang.

At least 73 records · Page 4Linked to original sources

arXiv2023

Enhancing Computation Pushdown for Cloud OLAP Databases

Network is a major bottleneck in modern cloud databases that adopt a storage-disaggregation architecture. Computation pushdown is a promising solution to tackle this issue, which offloads some computation tasks to the storage layer to reduce network traffic. Existing cloud OLAP systems statically decide whether to push down computation during the query optimization phase and do not consider the storage layer's computational capacity and load. Besides, there is a lack of a general principle that determines which operators are amenable for pushdown. Existing systems design and implement pushdown features empirically, which ends up picking a limited set of pushdown operators respectively. In this paper, we first design Adaptive pushdown as a new mechanism to avoid throttling the storage-layer computation during pushdown, which pushes the request back to the computation layer at runtime if the storage-layer computational resource is insufficient. Moreover, we derive a general principle to identify pushdown-amenable computational tasks, by summarizing common patterns of pushdown capabilities in existing systems. We propose two new pushdown operators, namely, selection bitmap and distributed data shuffle. Evaluation results on TPC-H show that Adaptive pushdown can achieve up to 1.9x speedup over both No pushdown and Eager pushdown baselines, and the new pushdown operators can further accelerate query execution by up to 3.0x.

cs.DB↗

arXiv2023

Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning

Detecting both known and unknown objects is a fundamental skill for robot manipulation in unstructured environments. Open-set object detection (OSOD) is a promising direction to handle the problem consisting of two subtasks: objects and background separation, and open-set object classification. In this paper, we present Openset RCNN to address the challenging OSOD. To disambiguate unknown objects and background in the first subtask, we propose to use classification-free region proposal network (CF-RPN) which estimates the objectness score of each region purely using cues from object's location and shape preventing overfitting to the training categories. To identify unknown objects in the second subtask, we propose to represent them using the complementary region of known categories in a latent space which is accomplished by a prototype learning network (PLN). PLN performs instance-level contrastive learning to encode proposals to a latent space and builds a compact region centering with a prototype for each known category. Further, we note that the detection performance of unknown objects can not be unbiasedly evaluated on the situation that commonly used object detection datasets are not fully annotated. Thus, a new benchmark is introduced by reorganizing GraspNet-1billion, a robotic grasp pose detection dataset with complete annotation. Extensive experiments demonstrate the merits of our method. We finally show that our Openset RCNN can endow the robot with an open-set perception ability to support robotic rearrangement tasks in cluttered environments. More details can be found in https://sites.google.com/view/openset-rcnn/

cs.CV↗

arXiv2023

RefGPT: Dialogue Generation of GPT, by GPT, and for GPT

Large Language Models (LLMs) have attained the impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data. However, collecting human-written data of high quality, especially multi-turn dialogues, is expensive and unattainable for most people. Though previous studies have used powerful LLMs to generate the dialogues automatically, they all suffer from generating untruthful dialogues because of the model hallucination. Therefore, we propose a method called RefGPT to generate enormous truthful and customized dialogues without worrying about factual errors caused by the model hallucination. RefGPT solves the model hallucination in dialogue generation by restricting the LLMs to leverage the given reference instead of reciting their own knowledge to generate dialogues. Additionally, RefGPT adds detailed controls on every utterance to enable high customization capability, which previous studies have ignored. On the basis of RefGPT, we also propose two high-quality dialogue datasets generated by GPT-4, namely RefGPT-Fact and RefGPT-Code. RefGPT-Fact is a dataset with 100k multi-turn dialogues based on factual knowledge and RefGPT-Code has 76k multi-turn dialogues covering a wide range of coding scenarios. Our code and datasets are released in https://github.com/mutonix/RefGPT.

cs.CL↗

arXiv2023

BatGPT: A Bidirectional Autoregessive Talker from Generative Pre-trained Transformer

BatGPT is a large-scale language model designed and trained jointly by Wuhan University and Shanghai Jiao Tong University. It is capable of generating highly natural and fluent text in response to various types of input, including text prompts, images, and audio. In the modeling level, we employ a bidirectional autoregressive architecture that allows the model to efficiently capture the complex dependencies of natural language, making it highly effective in tasks such as language generation, dialog systems, and question answering. Moreover, the bidirectional autoregressive modeling not only operates from left to right but also from right to left, effectively reducing fixed memory effects and alleviating model hallucinations. In the training aspect, we propose a novel parameter expansion method for leveraging the pre-training of smaller models and employ reinforcement learning from both AI and human feedback, aimed at improving the model's alignment performance. Overall, these approaches significantly improve the effectiveness of BatGPT, and the model can be utilized for a wide range of natural language applications.

cs.CL↗

arXiv2023

Room Temperature Spin to Charge Conversion in Amorphous Topological Insulating Gd-Alloyed BixSe1-x/CoFeB Bilayers

Disordered topological insulator (TI) films have gained intense interest by benefiting from both the TIs exotic transport properties and the advantage of mass production by sputtering. Here, we report on the clear evidence of spin-charge conversion (SCC) in amorphous Gd-alloyed BixSe1-x (BSG)/CoFeB bilayers fabricated by sputtering, which could be related to the amorphous TI surface states. Two methods have been employed to study SCC in BSG/CoFeB(5 nm) bilayers with different BSG thicknesses. Firstly, spin pumping is used to generate a spin current in CoFeB and to detect SCC by inverse Edelstein effect. The maximum SCC efficiency (SCE) is measured as large as 0.035 nm in a 6 nm thick BSG sample, which shows a strong decay when tBSG increases due to the increase of BSG surface roughness. The second method is the THz time-domain spectroscopy, which reveals a small tBSG dependence of SCE, validating the occurrence of a pure interface state related SCC. Furthermore, our angle-resolved photoemission spectroscopy data show dispersive two-dimensional surface states that cross the bulk gap until to the Fermi level, strengthening the possibility of SCC due to the amorphous TI states. Our studies provide a new experimental direction towards the search for topological systems in the amorphous solids.

cond-mat.mtrl-sci↗

arXiv2023

Observation and enhancement of room temperature bilinear magnetoelectric resistance in sputtered topological semimetal Pt3Sn

Topological semimetal materials have become a research hotspot due to their intrinsic strong spin-orbit coupling which leads to large charge-to-spin conversion efficiency and novel transport behaviors. In this work, we have observed a bilinear magnetoelectric resistance (BMER) of up to 0.1 nm2A-1Oe-1 in a singlelayer of sputtered semimetal Pt3Sn at room temperature. Different from previous observations, the value of BMER in sputtered Pt3Sn does not change out-of-plane due to the polycrystalline nature of Pt3Sn. The observation of BMER provides strong evidence of the existence of spin-momentum locking in the sputtered polycrystalline Pt3Sn. By adding an adjacent CoFeB magnetic layer, the BMER value of this bilayer system is doubled compared to the single Pt3Sn layer. This work broadens the material system in BMER study, which paves the way for the characterization of topological states and applications for spin memory and logic devices.

cond-mat.mtrl-sci↗

arXiv2023

Attack Named Entity Recognition by Entity Boundary Interference

Named Entity Recognition (NER) is a cornerstone NLP task while its robustness has been given little attention. This paper rethinks the principles of NER attacks derived from sentence classification, as they can easily violate the label consistency between the original and adversarial NER examples. This is due to the fine-grained nature of NER, as even minor word changes in the sentence can result in the emergence or mutation of any entities, resulting in invalid adversarial examples. To this end, we propose a novel one-word modification NER attack based on a key insight, NER models are always vulnerable to the boundary position of an entity to make their decision. We thus strategically insert a new boundary into the sentence and trigger the Entity Boundary Interference that the victim model makes the wrong prediction either on this boundary word or on other words in the sentence. We call this attack Virtual Boundary Attack (ViBA), which is shown to be remarkably effective when attacking both English and Chinese models with a 70%-90% attack success rate on state-of-the-art language models (e.g. RoBERTa, DeBERTa) and also significantly faster than previous methods.

cs.CL↗

arXiv2023

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

Generating photorealistic images with controllable camera pose and scene contents is essential for many applications including AR/VR and simulation. Despite the fact that rapid progress has been made in 3D-aware generative models, most existing methods focus on object-centric images and are not applicable to generating urban scenes for free camera viewpoint control and scene editing. To address this challenging task, we propose UrbanGIRAFFE, which uses a coarse 3D panoptic prior, including the layout distribution of uncountable stuff and countable objects, to guide a 3D-aware generative model. Our model is compositional and controllable as it breaks down the scene into stuff, objects, and sky. Using stuff prior in the form of semantic voxel grids, we build a conditioned stuff generator that effectively incorporates the coarse semantic and geometry information. The object layout prior further allows us to learn an object generator from cluttered scenes. With proper loss functions, our approach facilitates photorealistic 3D-aware image synthesis with diverse controllability, including large camera movement, stuff editing, and object manipulation. We validate the effectiveness of our model on both synthetic and real-world datasets, including the challenging KITTI-360 dataset.

cs.CV↗

arXiv2023

A mempolar transistor made from tellurium

The classic three-terminal electronic transistors and the emerging two-terminal ion-based memristors are complementary to each other in various nonconventional information processing systems in a heterogeneous integration approach, such as hybrid CMOS/memristive neuromorphic crossbar arrays. Recent attempts to introduce transitive functions into memristors have given rise to gate-tunable memristive functions, hetero-plasticity and mixed-plasticity functions. However, it remains elusive under what application scenarios and in what ways transistors can benefit from the incorporation of ion-based memristive effects. Here, we introduce a new type of transistor named 'mempolar transistor' to the transistor family. Its polarity can be converted reversibly, in a nonvolatile fashion, between n-type and p-type depending on the history of the applied electrical stimulus. This is achieved by the use of the emerging semiconducting tellurium as the electrochemically active source/drain contact material, in combination with monolayer two-dimensional MoS2 channel, which results in a gated lateral Te/MoS2/Te memristor, or from a different perspective, a transistor whose channel can be converted reversibly between n-type MoS2 and p-type Te. With this unique mempolar function, our transistor holds the promise for reconfigurable logic circuits and secure circuits. In addition, we propose and demonstrate experimentally, a ternary content-addressable memory made of only two mempolar transistors, which used to require a dozen normal transistors, and by simulations, a device-inspired and hardware matched regularization method 'FlipWeight' for training artificial neural networks, which can achieve comparable performance to that achieved by the prevalent 'Dropout' and 'DropConnect' methods. This work represents a major advance in diversifying the functionality of transistors.

physics.app-ph↗

arXiv2022

Bio-realistic and versatile artificial dendrites made of anti-ambipolar transistors

The understanding of neural networks as neuron-synapse binaries has been the foundation of neuroscience, and therefore, the emerging neuromorphic computing technology that takes inspiration from the brain. This dogma, however, has been increasingly challenged by recent neuroscience research in which the downplayed dendrites were found to be active, dynamically unique and computationally powerful. To date, research on artificial dendrites is scarce and the few existing devices are still far from versatile or (and) bio-realistic. A breakthrough is hampered by the limited available physical mechanisms in mainstream device architectures. Here, we experimentally demonstrate a bio-realistic and versatile artificial dendrite made of WSe2/MoS2 heterojunction-channel anti-ambipolar transistor, which can closely mimic the experimentally recorded non-monotonic dendritic Ca2+ action potential that underpins various sophisticated computations. Spiking neural network simulations reveal that the incorporation of this nonconventional but bio-realistic dendritic activation enhances the robustness and representational capability of the network in non-stationary environments. By further exploiting the memristive effect, dendritic anti-ambipolar transistor can naturally mimic Ca2+-mediated regulation of synaptic plasticity (meta-plasticity) at dendritic spine, an important homeostatic phenomenon due to dendritic modulation. The invention of dendritic anti-ambipolar transistor completes the family of neuromorphic transistors and represents a major advance in diversifying the functionality of transistors.

physics.app-ph↗

arXiv2022

Graph Neural Network Based Node Deployment for Throughput Enhancement

The recent rapid growth in mobile data traffic entails a pressing demand for improving the throughput of the underlying wireless communication networks. Network node deployment has been considered as an effective approach for throughput enhancement which, however, often leads to highly non-trivial non-convex optimizations. Although convex approximation based solutions are considered in the literature, their approximation to the actual throughput may be loose and sometimes lead to unsatisfactory performance. With this consideration, in this paper, we propose a novel graph neural network (GNN) method for the network node deployment problem. Specifically, we fit a GNN to the network throughput and use the gradients of this GNN to iteratively update the locations of the network nodes. Besides, we show that an expressive GNN has the capacity to approximate both the function value and the gradients of a multivariate permutation-invariant function, as a theoretic support to the proposed method. To further improve the throughput, we also study a hybrid node deployment method based on this approach. To train the desired GNN, we adopt a policy gradient algorithm to create datasets containing good training samples. Numerical experiments show that the proposed methods produce competitive results compared to the baselines.

cs.NI↗

arXiv2022

Nested Named Entity Recognition as Holistic Structure Parsing

As a fundamental natural language processing task and one of core knowledge extraction techniques, named entity recognition (NER) is widely used to extract information from texts for downstream tasks. Nested NER is a branch of NER in which the named entities (NEs) are nested with each other. However, most of the previous studies on nested NER usually apply linear structure to model the nested NEs which are actually accommodated in a hierarchical structure. Thus in order to address this mismatch, this work models the full nested NEs in a sentence as a holistic structure, then we propose a holistic structure parsing algorithm to disclose the entire NEs once for all. Besides, there is no research on applying corpus-level information to NER currently. To make up for the loss of this information, we introduce Point-wise Mutual Information (PMI) and other frequency features from corpus-aware statistics for even better performance by holistic modeling from sentence-level to corpus-level. Experiments show that our model yields promising results on widely-used benchmarks which approach or even achieve state-of-the-art. Further empirical studies show that our proposed corpus-aware features can substantially improve NER domain adaptation, which demonstrates the surprising advantage of our proposed corpus-level holistic structure modeling.

cs.CL↗

arXiv2021

Attend to the Difference: Cross-Modality Person Re-identification via Contrastive Correlation

The problem of cross-modality person re-identification has been receiving increasing attention recently, due to its practical significance. Motivated by the fact that human usually attend to the difference when they compare two similar objects, we propose a dual-path cross-modality feature learning framework which preserves intrinsic spatial strictures and attends to the difference of input cross-modality image pairs. Our framework is composed by two main components: a Dual-path Spatial-structure-preserving Common Space Network (DSCSN) and a Contrastive Correlation Network (CCN). The former embeds cross-modality images into a common 3D tensor space without losing spatial structures, while the latter extracts contrastive features by dynamically comparing input image pairs. Note that the representations generated for the input RGB and Infrared images are mutually dependant to each other. We conduct extensive experiments on two public available RGB-IR ReID datasets, SYSU-MM01 and RegDB, and our proposed method outperforms state-of-the-art algorithms by a large margin with both full and simplified evaluation modes.

cs.CV↗

arXiv2020

Improving unsupervised anomaly localization by applying multi-scale memories to autoencoders

Autoencoder and its variants have been widely applicated in anomaly detection.The previous work memory-augmented deep autoencoder proposed memorizing normality to detect anomaly, however it neglects the feature discrepancy between different resolution scales, therefore we introduce multi-scale memories to record scale-specific features and multi-scale attention fuser between the encoding and decoding module of the autoencoder for anomaly detection, namely MMAE.MMAE updates slots at corresponding resolution scale as prototype features during unsupervised learning. For anomaly detection, we accomplish anomaly removal by replacing the original encoded image features at each scale with most relevant prototype features,and fuse these features before feeding to the decoding module to reconstruct image. Experimental results on various datasets testify that our MMAE successfully removes anomalies at different scales and performs favorably on several datasets compared to similar reconstruction-based methods.

cs.CV↗

arXiv2020

Person Re-identification in Aerial Imagery

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), visual surveillance by utilizing the UAV platform has been very attractive. Most of the research works for UAV captured visual data are mainly focused on the tasks of object detection and tracking. However, limited attention has been paid to the task of person Re-identification (ReID) which has been widely studied in ordinary surveillance cameras with fixed emplacements. In this paper, to facilitate the research of person ReID in aerial imagery, we collect a large scale airborne person ReID dataset named as Person ReID for Aerial Imagery (PRAI-1581), which consists of 39,461 images of 1581 person identities. The images of the dataset are shot by two DJI consumer UAVs flying at an altitude ranging from 20 to 60 meters above the ground, which covers most of the real UAV surveillance scenarios. In addition, we propose to utilize subspace pooling of convolution feature maps to represent the input person images. Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently. We conduct extensive experiments on the proposed dataset and the experimental results demonstrate that re-identify persons in aerial imagery is a challenging problem, where our method performs favorably against state of the arts. Our dataset can be accessed via \url{https://github.com/stormyoung/PRAI-1581}.

cs.CV↗

arXiv2019

IRS-Enhanced OFDMA: Joint Resource Allocation and Passive Beamforming Optimization

Intelligent reflecting surface (IRS) is an emerging technique to enhance the wireless communication spectral efficiency with low hardware and energy cost. In this letter, we consider the integration of IRS to an orthogonal frequency division multiple access (OFDMA) based multiuser downlink communication system, and study the pertinent joint optimization of the IRS reflection coefficients and OFDMA time-frequency resource block as well as power allocations to maximize the users' common (minimum) rate. Specifically, due to the lack of frequency-selective passive beamforming capability at the IRS, only one set of reflection coefficients can be designed for adapting to a large number of channels of multiple users over different frequency sub-bands. To tackle this difficulty, we propose a novel dynamic passive beamforming scheme where the IRS reflection coefficients are dynamically adjusted over different time slots within each channel coherence block to create artificial time-varying channels and select only a subset of the users to be simultaneously served in each time slot, thus achieving a higher passive beamforming gain. Although the formulated optimization problem is non-convex, we propose an efficient algorithm to obtain a suboptimal solution to it. Numerical results show that the proposed scheme significantly improves the system common rate over the setup without IRS and that with random IRS reflection coefficients. Moreover, our proposed dynamic passive beamforming outperforms the fixed passive beamforming which employs a common set of reflection coefficients in each channel coherence block, by more flexibly balancing between passive beamforming and multiuser diversity gains.

cs.IT↗

arXiv2019

Intelligent Reflecting Surface Meets OFDM: Protocol Design and Rate Maximization

Intelligent reflecting surface (IRS) is a promising new technology for achieving both spectrum and energy efficient wireless communication systems in the future. However, existing works on IRS mainly consider frequency-flat channels and assume perfect knowledge of channel state information (CSI) at the transmitter. Motivated by this, in this paper we study an IRS-enhanced orthogonal frequency division multiplexing (OFDM) system under frequency-selective channels and propose a practical transmission protocol with channel estimation. First, to reduce the overhead in channel training and estimation and to exploit the channel spatial correlation, we propose a novel IRS elements grouping method, where each group consists of a set of adjacent IRS elements that share a common reflection coefficient. Based on this grouping method, we propose a practical transmission protocol where only the combined channel of each group needs to be estimated, thus substantially reducing the training overhead. Next, with any given grouping and estimated CSI, we formulate the problem to maximize the achievable rate by jointly optimizing the transmit power allocation and the IRS passive array reflection coefficients. Although the formulated problem is non-convex and thus difficult to solve, we propose an efficient algorithm to obtain a high-quality suboptimal solution for it, by alternately optimizing the power allocation and the passive array coefficients in an iterative manner, along with a customized method for the initialization. Simulation results show that the proposed design significantly improves the OFDM link rate performance as compared to the case without using IRS. Moreover, it is shown that there exists an optimal size for IRS elements grouping which achieves the maximum achievable rate due to the trade-off between the training overhead and IRS passive beamforming flexibility.

cs.IT↗

arXiv2019

IRS-Enhanced OFDM: Power Allocation and Passive Array Optimization

Intelligent reflecting surface (IRS) is a promising new technology for achieving spectrum and energy efficient wireless communication systems in the future. By adaptively varying the incident signals' phases/amplitudes and thereby establishing favorable channel responses through a large number of reconfigurable passive reflecting elements, IRS is able to enhance the communication performance of mobile users in its vicinity cost-effectively. In this paper, we study an IRS-enhanced orthogonal frequency division multiplexing (OFDM) system in which an IRS is deployed to assist the communication between a nearby user and its associated base station (BS). We aim to maximize the downlink achievable rate for the user by jointly optimizing the transmit power allocation at the BS and the passive array reflection coefficients at the IRS. Although the formulated problem is non-convex and thus difficult to solve, we propose an efficient algorithm to obtain a high-quality suboptimal solution for it, by alternately optimizing the BS's power allocation and the IRS's passive array coefficients in an iterative manner, along with a customized method for the initialization. Simulation results show that the proposed design significantly improves the OFDM link rate performance as compared to the cases without the IRS or with other heuristic IRS designs.

eess.SP↗