arXiv subjects

Chao Li

Publications and source records attributed to Chao Li.

At least 397 records · Page 22Linked to original sources

arXiv2022

SP-ViT: Learning 2D Spatial Priors for Vision Transformers

Recently, transformers have shown great potential in image classification and established state-of-the-art results on the ImageNet benchmark. However, compared to CNNs, transformers converge slowly and are prone to overfitting in low-data regimes due to the lack of spatial inductive biases. Such spatial inductive biases can be especially beneficial since the 2D structure of an input image is not well preserved in transformers. In this work, we present Spatial Prior-enhanced Self-Attention (SP-SA), a novel variant of vanilla Self-Attention (SA) tailored for vision transformers. Spatial Priors (SPs) are our proposed family of inductive biases that highlight certain groups of spatial relations. Unlike convolutional inductive biases, which are forced to focus exclusively on hard-coded local regions, our proposed SPs are learned by the model itself and take a variety of spatial relations into account. Specifically, the attention score is calculated with emphasis on certain kinds of spatial relations at each head, and such learned spatial foci can be complementary to each other. Based on SP-SA we propose the SP-ViT family, which consistently outperforms other ViT models with similar GFlops or parameters. Our largest model SP-ViT-L achieves a record-breaking 86.3% Top-1 accuracy with a reduction in the number of parameters by almost 50% compared to previous state-of-the-art model (150M for SP-ViT-L vs 271M for CaiT-M-36) among all ImageNet-1K models trained on 224x224 and fine-tuned on 384x384 resolution w/o extra data.

cs.CV↗

arXiv2022

Permutation Search of Tensor Network Structures via Local Sampling

Recent works put much effort into tensor network structure search (TN-SS), aiming to select suitable tensor network (TN) structures, involving the TN-ranks, formats, and so on, for the decomposition or learning tasks. In this paper, we consider a practical variant of TN-SS, dubbed TN permutation search (TN-PS), in which we search for good mappings from tensor modes onto TN vertices (core tensors) for compact TN representations. We conduct a theoretical investigation of TN-PS and propose a practically-efficient algorithm to resolve the problem. Theoretically, we prove the counting and metric properties of search spaces of TN-PS, analyzing for the first time the impact of TN structures on these unique properties. Numerically, we propose a novel meta-heuristic algorithm, in which the searching is done by randomly sampling in a neighborhood established in our theory, and then recurrently updating the neighborhood until convergence. Numerical results demonstrate that the new algorithm can reduce the required model size of TNs in extensive benchmarks, implying the improvement in the expressive power of TNs. Furthermore, the computational cost for the new algorithm is significantly less than that in~\cite{li2020evolutionary}.

cs.LG↗

arXiv2022

Blockchain-based Transparency Framework for Privacy Preserving Third-party Services

Increasingly, information systems rely on computational, storage, and network resources deployed in third-party facilities such as cloud centers and edge nodes. Such an approach further exacerbates cybersecurity concerns constantly raised by numerous incidents of security and privacy attacks resulting in data leakage and identity theft, among others. These have, in turn, forced the creation of stricter security and privacy-related regulations and have eroded the trust in cyberspace. In particular, security-related services and infrastructures, such as Certificate Authorities (CAs) that provide digital certificate services and Third-Party Authorities (TPAs) that provide cryptographic key services, are critical components for establishing trust in crypto-based privacy-preserving applications and services. To address such trust issues, various transparency frameworks and approaches have been recently proposed in the literature. This paper proposes TAB framework that provides transparency and trustworthiness of third-party authority and third-party facilities using blockchain techniques for emerging crypto-based privacy-preserving applications. TAB employs the Ethereum blockchain as the underlying public ledger and also includes a novel smart contract to automate accountability with an incentive mechanism that motivates users to participate in auditing, and punishes unintentional or malicious behaviors. We implement TAB and show through experimental evaluation in the Ethereum official test network, Rinkeby, that the framework is efficient. We also formally show the security guarantee provided by TAB, and analyze the privacy guarantee and trustworthiness it provides.

cs.CR↗

arXiv2022

PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration

Deep learning has achieved impressive results in many areas, but the deployment of edge intelligent devices is still very slow. To solve this problem, we propose a novel compression and acceleration method based on data distribution characteristics for deep neural networks, namely Pruning Filter via Gaussian Distribution Feature (PFGDF). Compared with previous advanced pruning methods, PFGDF compresses the model by filters with insignificance in distribution, regardless of the contribution and sensitivity information of the convolution filter. PFGDF is significantly different from weight sparsification pruning because it does not require the special accelerated library to process the sparse weight matrix and introduces no more extra parameters. The pruning process of PFGDF is automated. Furthermore, the model compressed by PFGDF can restore the same performance as the uncompressed model. We evaluate PFGDF through extensive experiments, on CIFAR-10, PFGDF compresses the convolution filter on VGG-16 by 66.62% with more than 90% parameter reduced, while the inference time is accelerated by 83.73% on Huawei MATE 10.

cs.CV↗

arXiv2022

DRLinFluids -- An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM

We propose an open-source python platform for applications of Deep Reinforcement Learning (DRL) in fluid mechanics. DRL has been widely used in optimizing decision-making in nonlinear and high-dimensional problems. Here, an agent maximizes a cumulative reward with learning a feedback policy by acting in an environment. In control theory terms, the cumulative reward would correspond to the cost function, the agent to the actuator, the environment to the measured signals and the learned policy to the feedback law. Thus, DRL assumes an interactive environment or, equivalently, control plant. The setup of a numerical simulation plant with DRL is challenging and time-consuming. In this work, a novel python platform, named DRLinFluids is developed for this purpose, with DRL for flow control and optimization problems in fluid mechanics. The simulations employ OpenFOAM as popular, flexible Navier-Stokes solver in industry and academia, and Tensorforce or Tianshou as widely used versatile DRL packages. The reliability and efficiency of DRLinFluids are demonstrated for two wake stabilization benchmark problems. DRLinFluids significantly reduces the application effort of DRL in fluid mechanics and is expected to greatly accelerates academic and industrial applications.

physics.flu-dyn↗

arXiv2022

A note on Tate's conjectures for abelian varieties

In this mostly expository note, we explain a proof of Tate's two conjectures [Tat65] for algebraic cycles of arbitrary codimension on certain products of elliptic curves and abelian surfaces over number fields.

math.NT↗

arXiv2022

Group sparse optimization for inpainting of random fields on the sphere

We propose a group sparse optimization model for inpainting of a square-integrable isotropic random field on the unit sphere, where the field is represented by spherical harmonics with random complex coefficients. In the proposed optimization model, the variable is an infinite-dimensional complex vector and the objective function is a real-valued function defined by a hybrid of the $\ell_2$ norm and non-Liptchitz $\ell_p (0<p<1)$ norm that preserves rotational invariance property and group structure of the random complex coefficients. We show that the infinite-dimensional optimization problem is equivalent to a convexly-constrained finite-dimensional optimization problem. Moreover, we propose a smoothing penalty algorithm to solve the finite-dimensional problem via unconstrained optimization problems. We provide an approximation error bound of the inpainted random field defined by a scaled KKT point of the constrained optimization problem in the square-integrable space on the sphere with probability measure. Finally, we conduct numerical experiments on band-limited random fields on the sphere and images from Earth topography data to show the promising performance of the smoothing penalty algorithm for inpainting of random fields on the sphere.

math.OC↗

arXiv2022

Observation of biradical spin coupling through hydrogen bonds

Investigation of intermolecular electron spin interaction is of fundamental importance in both science and technology.Here, radical pairs of all-trans retinoic acid molecules on Au(111) are created using an ultra-low temperature scanning tunneling microscope. Antiferromagnetic coupling between two radicals is identified by magnetic-field dependent spectroscopy.The measured exchange energies are from 0.1 to 1.0 meV. The biradical spin coupling is mediated through O-H$\cdots$O hydrogen bonds, as elucidated from analysis combining density functional theory calculation and a modern version of valence bond theory.

cond-mat.mes-hall↗

arXiv2022

Gleo-Det: Deep Convolution Feature-Guided Detector with Local Entropy Optimization for Salient Points

Feature detection is an important procedure for image matching, where unsupervised feature detection methods are the detection approaches that have been mostly studied recently, including the ones that are based on repeatability requirement to define loss functions, and the ones that attempt to use descriptor matching to drive the optimization of the pipelines. For the former type, mean square error (MSE) is usually used which cannot provide strong constraint for training and can make the model easy to be stuck into the collapsed solution. For the later one, due to the down sampling operation and the expansion of receptive fields, the details can be lost for local descriptors can be lost, making the constraint not fine enough. Considering the issues above, we propose to combine both ideas, which including three aspects. 1) We propose to achieve fine constraint based on the requirement of repeatability while coarse constraint with guidance of deep convolution features. 2) To address the issue that optimization with MSE is limited, entropy-based cost function is utilized, both soft cross-entropy and self-information. 3) With the guidance of convolution features, we define the cost function from both positive and negative sides. Finally, we study the effect of each modification proposed and experiments demonstrate that our method achieves competitive results over the state-of-the-art approaches.

cs.CV↗

arXiv2022

Integrating Large Circular Kernels into CNNs through Neural Architecture Search

The square kernel is a standard unit for contemporary CNNs, as it fits well on the tensor computation for convolution operation. However, the retinal ganglion cells in the biological visual system have approximately concentric receptive fields. Motivated by this observation, we propose to use circular kernel with a concentric and isotropic receptive field as an option for the convolution operation. We first propose a simple yet efficient implementation of the convolution using circular kernels, and empirically show the significant advantages of large circular kernels over the counterpart square kernels. We then expand the operation space of several typical Neural Architecture Search (NAS) methods with the convolutions of large circular kernels. The searched new neural architectures do contain large circular kernels and outperform the original searched models considerably. Our additional analysis also reveals that large circular kernels could help the model to be more robust to the rotated or sheared images due to their better rotation invariance. Our work shows the potential of designing new convolutional kernels for CNNs, bringing up the prospect of expanding the search space of NAS with new variants of convolutions.

cs.CV↗

arXiv2022

Multi-modal learning for predicting the genotype of glioma

The isocitrate dehydrogenase (IDH) gene mutation is an essential biomarker for the diagnosis and prognosis of glioma. It is promising to better predict glioma genotype by integrating focal tumor image and geometric features with brain network features derived from MRI. Convolutions neural networks show reasonable performance in predicting IDH mutation, which, however, cannot learn from non-Euclidean data, e.g., geometric and network data. In this study, we propose a multi-modal learning framework using three separate encoders to extract features of focal tumor image, tumor geometrics and global brain networks. To mitigate the limited availability of diffusion MRI, we develop a self-supervised approach to generate brain networks from anatomical multi-sequence MRI. Moreover, to extract tumor-related features from the brain network, we design a hierarchical attention module for the brain network encoder. Further, we design a bi-level multi-modal contrastive loss to align the multi-modal features and tackle the domain gap at the focal tumor and global brain. Finally, we propose a weighted population graph to integrate the multi-modal features for genotype prediction. Experimental results on the testing set show that the proposed model outperforms the baseline deep learning models. The ablation experiments validate the performance of different components of the framework. The visualized interpretation corresponds to clinical knowledge with further validation. In conclusion, the proposed learning framework provides a novel approach for predicting the genotype of glioma.

cs.CV↗

arXiv2022

Type-Driven Multi-Turn Corrections for Grammatical Error Correction

Grammatical Error Correction (GEC) aims to automatically detect and correct grammatical errors. In this aspect, dominant models are trained by one-iteration learning while performing multiple iterations of corrections during inference. Previous studies mainly focus on the data augmentation approach to combat the exposure bias, which suffers from two drawbacks. First, they simply mix additionally-constructed training instances and original ones to train models, which fails to help models be explicitly aware of the procedure of gradual corrections. Second, they ignore the interdependence between different types of corrections. In this paper, we propose a Type-Driven Multi-Turn Corrections approach for GEC. Using this approach, from each training instance, we additionally construct multiple training instances, each of which involves the correction of a specific type of errors. Then, we use these additionally-constructed training instances and the original one to train the model in turn. Experimental results and in-depth analysis show that our approach significantly benefits the model training. Particularly, our enhanced model achieves state-of-the-art single-model performance on English GEC benchmarks. We release our code at Github.

cs.CL↗

arXiv2022

An Ultra-Compact Single FeFET Binary and Multi-Bit Associative Search Engine

Content addressable memory (CAM) is widely used in associative search tasks for its highly parallel pattern matching capability. To accommodate the increasingly complex and data-intensive pattern matching tasks, it is critical to keep improving the CAM density to enhance the performance and area efficiency. In this work, we demonstrate: i) a novel ultra-compact 1FeFET CAM design that enables parallel associative search and in-memory hamming distance calculation; ii) a multi-bit CAM for exact search using the same CAM cell; iii) compact device designs that integrate the series resistor current limiter into the intrinsic FeFET structure to turn the 1FeFET1R into an effective 1FeFET cell; iv) a successful 2-step search operation and a sufficient sensing margin of the proposed binary and multi-bit 1FeFET1R CAM array with sizes of practical interests in both experiments and simulations, given the existing unoptimized FeFET device variation; v) 89.9x speedup and 66.5x energy efficiency improvement over the state-of-the art alignment tools on GPU in accelerating genome pattern matching applications through the hyperdimensional computing paradigm.

cs.ET↗

arXiv2022

Ego4D: Around the World in 3,000 Hours of Egocentric Video

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

cs.CV↗

arXiv2022

Exploring Structural Sparsity in Neural Image Compression

Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP). However,their sophisticated network structures with cascaded convolution layers bring heavy computational burden for practical deployment. In this paper, we explore the structural sparsity in neural image compression network to obtain real-time acceleration without any specialized hardware design or algorithm. We propose a simple plug-in adaptive binary channel masking(ABCM) to judge the importance of each convolution channel and introduce sparsity during training. During inference, the unimportant channels are pruned to obtain slimmer network and less computation. We implement our method into three neural image compression networks with different entropy models to verify its effectiveness and generalization, the experiment results show that up to 7x computation reduction and 3x acceleration can be achieved with negligible performance drop.

eess.IV↗

arXiv2022

Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems

Math Word Problem (MWP) solving needs to discover the quantitative relationships over natural language narratives. Recent work shows that existing models memorize procedures from context and rely on shallow heuristics to solve MWPs. In this paper, we look at this issue and argue that the cause is a lack of overall understanding of MWP patterns. We first investigate how a neural network understands patterns only from semantics, and observe that, if the prototype equations are the same, most problems get closer representations and those representations apart from them or close to other prototypes tend to produce wrong solutions. Inspired by it, we propose a contrastive learning approach, where the neural network perceives the divergence of patterns. We collect contrastive examples by converting the prototype equation into a tree and seeking similar tree structures. The solving model is trained with an auxiliary objective on the collected examples, resulting in the representations of problems with similar prototypes being pulled closer. We conduct experiments on the Chinese dataset Math23k and the English dataset MathQA. Our method greatly improves the performance in monolingual and multilingual settings.

cs.CL↗

arXiv2022

Predicting conversion of mild cognitive impairment to Alzheimer's disease

Alzheimer's disease (AD) is the most common age-related dementia. Mild cognitive impairment (MCI) is the early stage of cognitive decline before AD. It is crucial to predict the MCI-to-AD conversion for precise management, which remains challenging due to the diversity of patients. Previous evidence shows that the brain network generated from diffusion MRI promises to classify dementia using deep learning. However, the limited availability of diffusion MRI challenges the model training. In this study, we develop a self-supervised contrastive learning approach to generate structural brain networks from routine anatomical MRI under the guidance of diffusion MRI. The generated brain networks are applied to train a learning framework for predicting the MCI-to-AD conversion. Instead of directly modelling the AD brain networks, we train a graph encoder and a variational autoencoder to model the healthy ageing trajectories from brain networks of healthy controls. To predict the MCI-to-AD conversion, we further design a recurrent neural networks based approach to model the longitudinal deviation of patients' brain networks from the healthy ageing trajectory. Numerical results show that the proposed methods outperform the benchmarks in the prediction task. We also visualize the model interpretation to explain the prediction and identify abnormal changes of white matter tracts.

eess.IV↗

arXiv2022

The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking

Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors, which are mainly caused by the phonological or visual similarity. Recently, pre-trained language models (PLMs) promote the progress of CSC task. However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task. PLMs focus on the semantics in text and tend to correct the erroneous characters to semantically proper or commonly used ones, but these aren't the ground-truth corrections. To address this issue, we propose an Error-driven COntrastive Probability Optimization (ECOPO) framework for CSC task. ECOPO refines the knowledge representations of PLMs, and guides the model to avoid predicting these common characters through an error-driven way. Particularly, ECOPO is model-agnostic and it can be combined with existing CSC methods to achieve better performance. Extensive experiments and detailed analyses on SIGHAN datasets demonstrate that ECOPO is simple yet effective.

cs.CL↗