arXiv subjects

Chao Li

Publications and source records attributed to Chao Li.

At least 415 records · Page 23Linked to original sources

arXiv2022

On The Design of a Light-weight FPGA Programming Framework for Graph Applications

FPGA accelerators designed for graph processing are gaining popularity. Domain Specific Language (DSL) frameworks for graph processing can reduce the programming complexity and development cost of algorithm design. However, accelerator-specific development requires certain technical expertise and significant effort to devise, implement, and validate the system. For most algorithm designers, the expensive cost for hardware programming experience makes FPGA accelerators either unavailable or uneconomic. Although general-purpose High-Level Synthesis (HLS) tools help to map high-level language to Hardware Description Languages (HDLs), the generated code is often inefficient and lengthy compared with the highly-optimized graph accelerators. One cannot make full use of an FPGA accelerator's capacity with low development cost. To easily program graph algorithms while keeping performance degradation acceptable, we propose a graph programming system named JGraph, which contains two main parts: 1) a DSL for graph atomic operations with a graph library for high-level abstractions including user-defined functions with parameters, 2) a light-weight HLS translator to generate high-performance HDL code, cooperating with a communication manager and a runtime scheduler. To the best of our knowledge, our work is the first graph programming system with DSL and translator on the FPGA platform. Our system can generate up to 300 MTEPS BFS traversal within tens of seconds.

cs.AR↗

arXiv2022

A Hybrid mmWave and Camera System for Long-Range Depth Imaging

mmWave radars offer excellent depth resolution even at very long ranges owing to their high bandwidth. But their angular resolution is at least an order-of-magnitude worse than camera and lidar systems. Hence, mmWave radar is not a capable 3-D imaging solution in isolation. We propose Metamoran, a system that combines the complimentary strengths of radar and camera to obtain accurate, high resolution depth images over long ranges even in high clutter environments, all from a single fixed vantage point. Metamoran enables rich long-range depth imaging with applications in security and surveillance, roadside safety infrastructure and wide-area mapping. Our approach leverages the high angular resolution from cameras using computer vision techniques, including image segmentation and monocular depth estimation, to obtain object shape. Our core contribution is a method to convert this object shape into an RF I/Q equivalent, which we use in a novel radar processing pipeline to help declutter the scene and capture extremely weak reflections from objects at long distances. We perform a detailed evaluation of Metamoran's depth imaging capabilities in 400 diverse scenes. Our evaluation shows that Metamoran estimates the depth of static objects up to 90 m and moving objects up to 305 m and with a median error of 28 cm, an improvement of 13$\times$ compared to a naive radar+camera baseline and 23$\times$ compared to monocular depth estimation.

cs.CV↗

arXiv2022

Universal Efficient Variable-rate Neural Image Compression

Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate flexibility are still two major challenges for its practical deployment. To tackle these problems, this paper proposes two universal modules named Energy-based Channel Gating(ECG) and Bit-rate Modulator(BM), which can be directly embedded into existing end-to-end image compression models. ECG uses dynamic pruning to reduce FLOPs for more than 50\% in convolution layers, and a BM pair can modulate the latent representation to control the bit-rate in a channel-wise manner. By implementing these two modules, existing learning-based image codecs can obtain ability to output arbitrary bit-rate with a single model and reduced computation.

eess.IV↗

arXiv2022

Collimated versatile atomic beam source with alkali dispensers

Alkali metal dispensers have become an indispensable tool in the production of atomic vapors for magnetometry, alkali vapor cell clocks, and laser cooling experiments. A primary advantage of these dispensers is that they contain alkali metal in an inert form that can be exposed to air without hazard. However, their high temperature of operation (>600 C) is undesirable for many applications, as it shifts the atomic speed distribution to higher values and presents a radiative heat source that can raise the temperature of its surroundings. For this reason, dispensers are typically not used in line-of-sight applications such as atomic beam generation. In this work, we present an integrated rubidium dispenser collimating device with a thickness of only 2 mm that produces a beam of atoms traveling primarily in the forward direction. We find that the collimator plate serves to both shield the dispenser's radiation as well as to moderate the velocity of the atomic beam so that the measured longitudinal speed distribution is comparable to that of an ordinary alkali oven at only a slightly elevated temperature of 200 C. To confirm our theory, we also constructed another compact apparatus consisting of a dispenser and a silicon collimator and the measurements support our conclusion. Our integrated dispenser collimator will particularly be useful in integrated photonics and cavity QED on chip, where a localized, directed source of Rb vapor in small quantities is needed.

physics.atom-ph↗

arXiv2022

Classifying sufficiently connected PSC manifolds in $4$ and $5$ dimensions

We show that if $N$ is a closed manifold of dimension $n=4$ (resp. $n=5$) with $π_2(N) = 0$ (resp. $π_2(N)=π_3(N)=0$) that admits a metric of positive scalar curvature, then a finite cover $\hat N$ of $N$ is homotopy equivalent to $S^n$ or connected sums of $S^{n-1}\times S^1$. Our approach combines recent advances in the study of positive scalar curvature with a novel argument of Alpert--Balitskiy--Guth. Additionally, we prove a more general mapping version of this result. In particular, this implies that if $N$ is a closed manifold of dimensions $4$ or $5$, and $N$ admits a map of nonzero degree to a closed aspherical manifold, then $N$ does not admit any Riemannian metric with positive scalar curvature.

math.DG↗

arXiv2022

Characterizations and constructions of n-to-1 mappings over finite fields

$n$-to-$1$ mappings have wide applications in many areas, especially in cryptography, finite geometry, coding theory and combinatorial design. In this paper, many classes of $n$-to-$1$ mappings over finite fields are studied. First, we provide a characterization of general $n$-to-$1$ mappings over $\mathbb{F}_{p^m}$ by means of the Walsh transform. Then, we completely determine $3$-to-$1$ polynomials with degree no more than $4$ over $\mathbb{F}_{p^{m}}$. Furthermore, we obtain an AGW-like criterion for characterizing an equivalent relationship between the $n$-to-$1$ property of a mapping over finite set $A$ and that of another mapping over a subset of $A$. Finally, we apply the AGW-like criterion into several forms of polynomials and obtain some explicit $n$-to-$1$ mappings. Especially, three explicit constructions of the form $x^rh\left( x^s \right) $ from the cyclotomic perspective, and several classes of $n$-to-$1$ mappings of the form $ g\left( x^{q^k} -x +δ\right) +cx$ are provided.

cs.IT↗

arXiv2022

VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling

Deep learning (DL) models have achieved great success in many application domains. As such, many industrial companies such as Google and Facebook have acknowledged the importance of multi-tenant DL services. Although the multi-tenant service has been studied in conventional workloads, it is not been deeply studied on deep learning service, especially on general-purpose hardware. In this work, we systematically analyze the opportunities and challenges of providing multi-tenant deep learning services on the general-purpose CPU architecture from the aspects of scheduling granularity and code generation. We propose an adaptive granularity scheduling scheme to both guarantee resource usage efficiency and reduce the scheduling conflict rate. We also propose an adaptive compilation strategy, by which we can dynamically and intelligently pick a program with proper exclusive and shared resource usage to reduce overall interference-induced performance loss. Compared to the existing works, our design can serve more requests under the same QoS target in various scenarios (e.g., +71%, +62%, +45% for light, medium, and heavy workloads, respectively), and reduce the averaged query latency by 50%.

cs.DC↗

arXiv2022

Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma

The isocitrate dehydrogenase (IDH) gene mutation status is an important biomarker for glioma patients. The gold standard of IDH mutation detection requires tumour tissue obtained via invasive approaches and is usually expensive. Recent advancement in radiogenomics provides a non-invasive approach for predicting IDH mutation based on MRI. Meanwhile, tumor geometrics encompass crucial information for tumour phenotyping. Here we propose a collaborative learning framework that learns both tumor images and tumor geometrics using convolutional neural networks (CNN) and graph neural networks (GNN), respectively. Our results show that the proposed model outperforms the baseline model of 3D-DenseNet121. Further, the collaborative learning model achieves better performance than either the CNN or the GNN alone. The model interpretation shows that the CNN and GNN could identify common and unique regions of interest for IDH mutation prediction. In conclusion, collaborating image and geometric learners provides a novel approach for predicting genotype and characterising glioma.

cs.LG↗

arXiv2021

Architectural Implications of Graph Neural Networks

Graph neural networks (GNN) represent an emerging line of deep learning models that operate on graph structures. It is becoming more and more popular due to its high accuracy achieved in many graph-related tasks. However, GNN is not as well understood in the system and architecture community as its counterparts such as multi-layer perceptrons and convolutional neural networks. This work tries to introduce the GNN to our community. In contrast to prior work that only presents characterizations of GCNs, our work covers a large portion of the varieties for GNN workloads based on a general GNN description framework. By constructing the models on top of two widely-used libraries, we characterize the GNN computation at inference stage concerning general-purpose and application-specific architectures and hope our work can foster more system and architecture research for GNNs.

cs.AR↗

arXiv2021

Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning

Nowadays, Knowledge graphs (KGs) have been playing a pivotal role in AI-related applications. Despite the large sizes, existing KGs are far from complete and comprehensive. In order to continuously enrich KGs, automatic knowledge construction and update mechanisms are usually utilized, which inevitably bring in plenty of noise. However, most existing knowledge graph embedding (KGE) methods assume that all the triple facts in KGs are correct, and project both entities and relations into a low-dimensional space without considering noise and knowledge conflicts. This will lead to low-quality and unreliable representations of KGs. To this end, in this paper, we propose a general multi-task reinforcement learning framework, which can greatly alleviate the noisy data problem. In our framework, we exploit reinforcement learning for choosing high-quality knowledge triples while filtering out the noisy ones. Also, in order to take full advantage of the correlations among semantically similar relations, the triple selection processes of similar relations are trained in a collective way with multi-task learning. Moreover, we extend popular KGE models TransE, DistMult, ConvE and RotatE with the proposed framework. Finally, the experimental validation shows that our approach is able to enhance existing KGE models and can provide more robust representations of KGs in noisy scenarios.

cs.CL↗

arXiv2021

Unrestricted Adversarial Attacks on ImageNet Competition

Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this restriction. In fact, more threats to the deep model come from unrestricted adversarial examples, that is, the attacker makes large and visible modifications on the image, which causes the model classifying mistakenly, but does not affect the normal observation in human perspective. Unrestricted adversarial attack is a popular and practical direction but has not been studied thoroughly. We organize this competition with the purpose of exploring more effective unrestricted adversarial attack algorithm, so as to accelerate the academical research on the model robustness under stronger unbounded attacks. The competition is held on the TianChi platform (\url{https://tianchi.aliyun.com/competition/entrance/531853/introduction}) as one of the series of AI Security Challengers Program.

cs.CV↗

arXiv2021

Adversarial Attacks on ML Defense Models Competition

Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years. However, the progress of building more robust models is usually hampered by the incomplete or incorrect robustness evaluation. To accelerate the research on reliable evaluation of adversarial robustness of the current defense models in image classification, the TSAIL group at Tsinghua University and the Alibaba Security group organized this competition along with a CVPR 2021 workshop on adversarial machine learning (https://aisecure-workshop.github.io/amlcvpr2021/). The purpose of this competition is to motivate novel attack algorithms to evaluate adversarial robustness more effectively and reliably. The participants were encouraged to develop stronger white-box attack algorithms to find the worst-case robustness of different defenses. This competition was conducted on an adversarial robustness evaluation platform -- ARES (https://github.com/thu-ml/ares), and is held on the TianChi platform (https://tianchi.aliyun.com/competition/entrance/531847/introduction) as one of the series of AI Security Challengers Program. After the competition, we summarized the results and established a new adversarial robustness benchmark at https://ml.cs.tsinghua.edu.cn/ares-bench/, which allows users to upload adversarial attack algorithms and defense models for evaluation.

cs.CV↗

arXiv2021

Constrained deformations of positive scalar curvature metrics

We present a series of results concerning the interplay between the scalar curvature of a manifold and the mean curvature of its boundary. In particular, we give a complete topological characterization of those compact 3-manifolds that support Riemannian metrics of positive scalar curvature and mean-convex boundary and, in any such case, we prove that the associated moduli space of metrics is path-connected. The methods we employ are flexible enough to allow the construction of continuous paths of positive scalar curvature metrics with minimal boundary, and to derive similar conclusions in that context as well. Our work relies on a combination of earlier fundamental contributions by Gromov-Lawson and Schoen-Yau, on the smoothing procedure designed by Miao, and on the interplay of Perelman's Ricci flow with surgery and conformal deformation techniques introduced by Codá Marques in dealing with the closed case.

math.DG↗

arXiv2021

Deep Random Forest with Ferroelectric Analog Content Addressable Memory

Deep random forest (DRF), which incorporates the core features of deep learning and random forest (RF), exhibits comparable classification accuracy, interpretability, and low memory and computational overhead when compared with deep neural networks (DNNs) in various information processing tasks for edge intelligence. However, the development of efficient hardware to accelerate DRF is lagging behind its DNN counterparts. The key for hardware acceleration of DRF lies in efficiently realizing the branch-split operation at decision nodes when traversing a decision tree. In this work, we propose to implement DRF through simple associative searches realized with ferroelectric analog content addressable memory (ACAM). Utilizing only two ferroelectric field effect transistors (FeFETs), the ultra-compact ACAM cell can perform a branch-split operation with an energy-efficient associative search by storing the decision boundaries as the analog polarization states in an FeFET. The DRF accelerator architecture and the corresponding mapping of the DRF model to the ACAM arrays are presented. The functionality, characteristics, and scalability of the FeFET ACAM based DRF and its robustness against FeFET device non-idealities are validated both in experiments and simulations. Evaluation results show that the FeFET ACAM DRF accelerator exhibits 10^6x/16x and 10^6x/2.5x improvements in terms of energy and latency when compared with other deep random forest hardware implementations on the state-of-the-art CPU/ReRAM, respectively.

cs.ET↗

arXiv2021

Bayesian optimization assisted unsupervised learning for efficient intra-tumor partitioning in MRI and survival prediction for glioblastoma patients

Glioblastoma is profoundly heterogeneous in microstructure and vasculature, which may lead to tumor regional diversity and distinct treatment response. Although successful in tumor sub-region segmentation and survival prediction, radiomics based on machine learning algorithms, is challenged by its robustness, due to the vague intermediate process and track changes. Also, the weak interpretability of the model poses challenges to clinical application. Here we proposed a machine learning framework to semi-automatically fine-tune the clustering algorithms and quantitatively identify stable sub-regions for reliable clinical survival prediction. Hyper-parameters are automatically determined by the global minimum of the trained Gaussian Process (GP) surrogate model through Bayesian optimization(BO) to alleviate the difficulty of tuning parameters for clinical researchers. To enhance the interpretability of the survival prediction model, we incorporated the prior knowledge of intra-tumoral heterogeneity, by segmenting tumor sub-regions and extracting sub-regional features. The results demonstrated that the global minimum of the trained GP surrogate can be used as sub-optimal hyper-parameter solutions for efficient. The sub-regions segmented based on physiological MRI can be applied to predict patient survival, which could enhance the clinical interpretability for the machine learning model.

eess.IV↗

arXiv2021

Predicting isocitrate dehydrogenase mutation status in glioma using structural brain networks and graph neural networks

Glioma is a common malignant brain tumor with distinct survival among patients. The isocitrate dehydrogenase (IDH) gene mutation provides critical diagnostic and prognostic value for glioma. It is of crucial significance to non-invasively predict IDH mutation based on pre-treatment MRI. Machine learning/deep learning models show reasonable performance in predicting IDH mutation using MRI. However, most models neglect the systematic brain alterations caused by tumor invasion, where widespread infiltration along white matter tracts is a hallmark of glioma. Structural brain network provides an effective tool to characterize brain organisation, which could be captured by the graph neural networks (GNN) to more accurately predict IDH mutation. Here we propose a method to predict IDH mutation using GNN, based on the structural brain network of patients. Specifically, we firstly construct a network template of healthy subjects, consisting of atlases of edges (white matter tracts) and nodes (cortical/subcortical brain regions) to provide regions of interest (ROIs). Next, we employ autoencoders to extract the latent multi-modal MRI features from the ROIs of edges and nodes in patients, to train a GNN architecture for predicting IDH mutation. The results show that the proposed method outperforms the baseline models using the 3D-CNN and 3D-DenseNet. In addition, model interpretation suggests its ability to identify the tracts infiltrated by tumor, corresponding to clinical prior knowledge. In conclusion, integrating brain networks with GNN offers a new avenue to study brain lesions using computational neuroscience and computer vision approaches.

eess.IV↗

arXiv2021

L3C-Stereo: Lossless Compression for Stereo Images

A large number of autonomous driving tasks need high-definition stereo images, which requires a large amount of storage space. Efficiently executing lossless compression has become a practical problem. Commonly, it is hard to make accurate probability estimates for each pixel. To tackle this, we propose L3C-Stereo, a multi-scale lossless compression model consisting of two main modules: the warping module and the probability estimation module. The warping module takes advantage of two view feature maps from the same domain to generate a disparity map, which is used to reconstruct the right view so as to improve the confidence of the probability estimate of the right view. The probability estimation module provides pixel-wise logistic mixture distributions for adaptive arithmetic coding. In the experiments, our method outperforms the hand-crafted compression methods and the learning-based method on all three datasets used. Then, we show that a better maximum disparity can lead to a better compression effect. Furthermore, thanks to a compression property of our model, it naturally generates a disparity map of an acceptable quality for the subsequent stereo tasks.

eess.IV↗

arXiv2021

Adaptive unsupervised learning with enhanced feature representation for intra-tumor partitioning and survival prediction for glioblastoma

Glioblastoma is profoundly heterogeneous in regional microstructure and vasculature. Characterizing the spatial heterogeneity of glioblastoma could lead to more precise treatment. With unsupervised learning techniques, glioblastoma MRI-derived radiomic features have been widely utilized for tumor sub-region segmentation and survival prediction. However, the reliability of algorithm outcomes is often challenged by both ambiguous intermediate process and instability introduced by the randomness of clustering algorithms, especially for data from heterogeneous patients. In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction. A novel and problem-specific Feature-enhanced Auto-Encoder (FAE) is developed to enhance the representation of pairwise clinical modalities and therefore improve clustering stability of unsupervised learning algorithms such as K-means. Moreover, the entire process is modelled by the Bayesian optimization (BO) technique with a custom loss function that the hyper-parameters can be adaptively optimized in a reasonably few steps. The results demonstrate that the proposed approach can produce robust and clinically relevant MRI sub-regions and statistically significant survival predictions.

cs.LG↗