arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,099 records · Page 61Linked to original sources

arXiv2022

Consensus Learning for Cooperative Multi-Agent Reinforcement Learning

Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the global state. During decentralized execution, however, agents lack the shared signal. Inspired by viewpoint invariance and contrastive learning, we propose consensus learning for cooperative multi-agent reinforcement learning in this paper. Although based on local observations, different agents can infer the same consensus in discrete space. During decentralized execution, we feed the inferred consensus as an explicit input to the network of agents, thereby developing their spirit of cooperation. Our proposed method can be extended to various multi-agent reinforcement learning algorithms with small model changes. Moreover, we carry out them on some fully cooperative tasks and get convincing results.

cs.MA↗

arXiv2022

On Hull-Variation Problem of Equivalent Linear Codes

The intersection ${\bf C}\bigcap {\bf C}^{\perp}$ (${\bf C}\bigcap {\bf C}^{\perp_h}$) of a linear code ${\bf C}$ and its Euclidean dual ${\bf C}^{\perp}$ (Hermitian dual ${\bf C}^{\perp_h}$) is called the Euclidean (Hermitian) hull of this code. It is natural to consider the hull-variation problem when a linear code ${\bf C}$ is transformed to an equivalent code ${\bf v} \cdot {\bf C}$. In this paper we introduce the maximal hull dimension as an invariant of a linear code with respect to the equivalent transformations. Then some basic properties of the maximal hull dimension are studied. We prove that for a nonnegative integer $h$ satisfying $0 \leq h \leq n-1$, a linear $[2n, n]_q$ self-dual code is equivalent to a linear $h$-dimension hull code. On the opposite direction we prove that a linear LCD code over ${\bf F}_{2^s}$ satisfying $d\geq 2$ and $d^{\perp} \geq 2$ is equivalent to a linear one-dimension hull code under a weak condition. Several new families of LCD negacyclic codes and LCD BCH codes over ${\bf F}_3$ are also constructed. Our method can be applied to the generalized Reed-Solomon codes and the generalized twisted Reed-Solomon codes to construct arbitrary dimension hull MDS codes. Some new entanglement-assisted quantum error-correction (EAQEC) codes including MDS and almost MDS EAQEC codes are constructed. Many EAQEC codes over small fields are constructed from optimal Hermitian self-dual codes.

cs.IT↗

arXiv2022

The Liver Tumor Segmentation Benchmark (LiTS)

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in \url{http://medicaldecathlon.com/}. In addition, both data and online evaluation are accessible via \url{www.lits-challenge.com}.

cs.CV↗

arXiv2022

CNeRV: Content-adaptive Neural Representation for Visual Data

Compression and reconstruction of visual data have been widely studied in the computer vision community, even before the popularization of deep learning. More recently, some have used deep learning to improve or refine existing pipelines, while others have proposed end-to-end approaches, including autoencoders and implicit neural representations, such as SIREN and NeRV. In this work, we propose Neural Visual Representation with Content-adaptive Embedding (CNeRV), which combines the generalizability of autoencoders with the simplicity and compactness of implicit representation. We introduce a novel content-adaptive embedding that is unified, concise, and internally (within-video) generalizable, that compliments a powerful decoder with a single-layer encoder. We match the performance of NeRV, a state-of-the-art implicit neural representation, on the reconstruction task for frames seen during training while far surpassing for frames that are skipped during training (unseen images). To achieve similar reconstruction quality on unseen images, NeRV needs 120x more time to overfit per-frame due to its lack of internal generalization. With the same latent code length and similar model size, CNeRV outperforms autoencoders on reconstruction of both seen and unseen images. We also show promising results for visual data compression. More details can be found in the project pagehttps://haochen-rye.github.io/CNeRV/

cs.CV↗

arXiv2022

Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning-based Radiograph Diagnosis: A Multicenter Study

Two DL models were developed using radiograph-level annotations (yes or no disease) and fine-grained lesion-level annotations (lesion bounding boxes), respectively named CheXNet and CheXDet. The models' internal classification performance and lesion localization performance were compared on a testing set (n=2,922), external classification performance was compared on NIH-Google (n=4,376) and PadChest (n=24,536) datasets, and external lesion localization performance was compared on NIH-ChestX-ray14 dataset (n=880). The models were also compared to radiologists on a subset of the internal testing set (n=496). Given sufficient training data, both models performed comparably to radiologists. CheXDet achieved significant improvement for external classification, such as in classifying fracture on NIH-Google (CheXDet area under the ROC curve [AUC]: 0.67, CheXNet AUC: 0.51; p<.001) and PadChest (CheXDet AUC: 0.78, CheXNet AUC: 0.55; p<.001). CheXDet achieved higher lesion detection performance than CheXNet for most abnormalities on all datasets, such as in detecting pneumothorax on the internal set (CheXDet jacknife alternative free-response ROC-figure of merit [JAFROC-FOM]: 0.87, CheXNet JAFROC-FOM: 0.13; p<.001) and NIH-ChestX-ray14 (CheXDet JAFROC-FOM: 0.55, CheXNet JAFROC-FOM: 0.04; p<.001). To summarize, fine-grained annotations overcame shortcut learning and enabled DL models to identify correct lesion patterns, improving the models' generalizability.

eess.IV↗

arXiv2022

Helicoids and vortices

We point out an interesting connection between fluid dynamics and minimal surface theory: When gluing helicoids into a minimal surface, the limit positions of the helicoids correspond to a "vortex crystal", an equilibrium of point vortices in 2D fluid that move together as a rigid body. While vortex crystals have been studied for almost 150 years, the gluing construction of minimal surfaces is relatively new. As a consequence of the connection, we obtain many new minimal surfaces and some new vortex crystals by simply comparing notes.

math.DG↗

arXiv2022

Magnetic Resonance Spectroscopy Deep Learning Denoising Using Few In Vivo Data

Magnetic Resonance Spectroscopy (MRS) is a noninvasive tool to reveal metabolic information. One challenge of 1H-MRS is the low Signal-Noise Ratio (SNR). To improve the SNR, a typical approach is to perform Signal Averaging (SA) with M repeated samples. The data acquisition time, however, is increased by M times accordingly, and a complete clinical MRS scan takes approximately 10 minutes at a common setting M=128. Recently, deep learning has been introduced to improve the SNR but most of them use the simulated data as the training set. This may hinder the MRS applications since some potential differences, such as acquisition system imperfections, and physiological and psychologic conditions may exist between the simulated and in vivo data. Here, we proposed a new scheme that purely used the repeated samples of realistic data. A deep learning model, Refusion Long Short-Term Memory (ReLSTM), was designed to learn the mapping from the low SNR time-domain data (24 SA) to the high SNR one (128 SA). Experiments on the in vivo brain spectra of 7 healthy subjects, 2 brain tumor patients and 1 cerebral infarction patient showed that only using 20% repeated samples, the denoised spectra by ReLSTM could provide comparable estimated concentrations of metabolites to 128 SA. Compared with the state-of-the-art low-rank denoising method, the ReLSTM achieved the lower relative error and the Cramér-Rao lower bounds in quantifying some important biomarkers. In summary, ReLSTM can perform high-fidelity denoising of the spectra under fast acquisition (24 SA), which would be valuable to MRS clinical studies.

physics.med-ph↗

arXiv2022

Sequential Change-point Detection for High-dimensional and non-Euclidean Data

In many applications, it is often of practical and scientific interest to detect anomaly events in a streaming sequence of high-dimensional or non-Euclidean observations. We study a non-parametric framework that utilizes nearest neighbor information among the observations to detect changes in an online setting. It can be applied to data in arbitrary dimension and non-Euclidean data as long as a similarity measure on the sample space can be defined. We consider new test statistics under this framework that can detect anomaly events more effectively than the existing test while keeping the false discovery rate controlled at a fixed level. Analytic formulas approximating the average run lengths of the new approaches are derived to make them fast applicable to modern datasets. Simulation studies are provided to support theoretical results. The proposed approach is illustrated with an analysis of the NYC taxi dataset.

stat.ME↗

arXiv2022

Collinear Parton Dynamics Beyond DGLAP

Renormalization group evolution equations describing the scale dependence of quantities in quantum chromodynamics (QCD) play a central role in the interpretation of experimental data. Arguably the most important evolution equations for collider physics applications are the Dokshitzer-Gribov-Lipatov-Altarelli-Parisi (DGLAP) equations, which describe the evolution of a quark or gluon fragmenting into hadrons, with only a single hadron identified at a time. In recent years, the study of the correlations of energy flow within jets has come to play a central role at collider experiments, necessitating an understanding of correlations, going beyond the standard DGLAP paradigm. In this Letter we derive a general renormalization group equation describing the collinear dynamics that account for correlations in the fragmentation. We compute the kernel of this evolution equation at next-to-leading order (NLO), where it involves the $1\to 3$ splitting functions, and develop techniques to solve it numerically. We show that our equation encompasses all previously-known collinear evolution equations, namely DGLAP and the evolution of multi-hadron fragmentation functions. As an application of our results, we consider the phenomenologically-relevant example of energy flow on charged particles, computing the energy fraction in charged particles in $e^+e^- \to$ hadrons at NNLO. Our results are an important step towards improving the understanding of the collinear dynamics of jets, with broad applications in jet substructure, ranging from the study of multi-hadron correlations, to the description of inclusive (sub)jet production, and the advancement of modern parton showers.

hep-ph↗

arXiv2022

Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames

Cross-modal video retrieval aims to retrieve the semantically relevant videos given a text as a query, and is one of the fundamental tasks in Multimedia. Most of top-performing methods primarily leverage Visual Transformer (ViT) to extract video features [1, 2, 3], suffering from high computational complexity of ViT especially for encoding long videos. A common and simple solution is to uniformly sample a small number (say, 4 or 8) of frames from the video (instead of using the whole video) as input to ViT. The number of frames has a strong influence on the performance of ViT, e.g., using 8 frames performs better than using 4 frames yet needs more computational resources, resulting in a trade-off. To get free from this trade-off, this paper introduces an automatic video compression method based on a bilevel optimization program (BOP) consisting of both model-level (i.e., base-level) and frame-level (i.e., meta-level) optimizations. The model-level learns a cross-modal video retrieval model whose input is the "compressed frames" learned by frame-level optimization. In turn, the frame-level optimization is through gradient descent using the meta loss of video retrieval model computed on the whole video. We call this BOP method as well as the "compressed frames" as Meta-Optimized Frames (MOF). By incorporating MOF, the video retrieval model is able to utilize the information of whole videos (for training) while taking only a small number of input frames in actual implementation. The convergence of MOF is guaranteed by meta gradient descent algorithms. For evaluation, we conduct extensive experiments of cross-modal video retrieval on three large-scale benchmarks: MSR-VTT, MSVD, and DiDeMo. Our results show that MOF is a generic and efficient method to boost multiple baseline methods, and can achieve a new state-of-the-art performance.

cs.CV↗

arXiv2022

Planning Assembly Sequence with Graph Transformer

Assembly sequence planning (ASP) is the essential process for modern manufacturing, proven to be NP-complete thus its effective and efficient solution has been a challenge for researchers in the field. In this paper, we present a graph-transformer based framework for the ASP problem which is trained and demonstrated on a self-collected ASP database. The ASP database contains a self-collected set of LEGO models. The LEGO model is abstracted to a heterogeneous graph structure after a thorough analysis of the original structure and feature extraction. The ground truth assembly sequence is first generated by brute-force search and then adjusted manually to in line with human rational habits. Based on this self-collected ASP dataset, we propose a heterogeneous graph-transformer framework to learn the latent rules for assembly planning. We evaluated the proposed framework in a series of experiment. The results show that the similarity of the predicted and ground truth sequences can reach 0.44, a medium correlation measured by Kendall's $τ$. Meanwhile, we compared the different effects of node features and edge features and generated a feasible and reasonable assembly sequence as a benchmark for further research. Our data set and code is available on https://github.com/AIR-DISCOVER/ICRA\_ASP.

cs.AI↗

arXiv2022

USB: A Unified Semi-supervised Learning Benchmark for Classification

Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) for classification by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate the dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation of these SSL methods. We further provide the pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 39 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with TorchSSL.

cs.LG↗

arXiv2022

Better Lattice Quantizers Constructed from Complex Integers

This paper investigates low-dimensional quantizers from the perspective of complex lattices. We adopt Eisenstein integers and Gaussian integers to define checkerboard lattices $\mathcal{E}_{m}$ and $\mathcal{G}_{m}$. By explicitly linking their lattice bases to various forms of $\mathcal{E}_{m}$ and $\mathcal{G}_{m}$ cosets, we discover the $\mathcal{E}_{m,2}^+$ lattices, based on which we report the best known lattice quantizers in dimensions $14$, $15$, $18$, $19$, $22$ and $23$. Fast quantization algorithms of the generalized checkerboard lattices are proposed to enable evaluating the normalized second moment (NSM) through Monte Carlo integration.

cs.IT↗

arXiv2022

Electronic Origin of High-Tc Maximization and Persistence in Trilayer Cuprate Superconductors

In high temperature cuprate superconductors, it was found that the superconducting transition temperature Tc depends on the number of CuO2 planes (n) in the structural unit and the maximum Tc is realized in the trilayer system (n=3). It was also found that the trilayer superconductors exhibit an unusual phase diagram that Tc keeps nearly constant in the overdoped region which is in strong contrast to the Tc decrease usually found in other cuprate superconductors. The electronic origin of the Tc maximization in the trilayer superconductors and its high Tc persistence in the overdoped region remains unclear. By taking high resolution laser-based angle resolved photoemission (ARPES) measurements, here we report our revelation of the microscopic origin of the unusual superconducting properties in the trilayer superconductors. For the first time we have observed the trilayer splitting in Bi2Sr2Ca2Cu3O10+d (Bi2223) superconductor. The observed Fermi surface, band structures, superconducting gap and the selective Bogoliubov band hybridizations can be well described by a three-layer interaction model. Quantitative information of the microscopic processes involving intra- and interlayer hoppings and pairings are extracted. The electronic origin of the maximum Tc in Bi2223 and the persistence of the high Tc in the overdoped region is revealed. These results provide key insights in understanding high Tc superconductivity and pave a way to further enhance Tc in the cuprate superconductors.

cond-mat.supr-con↗

arXiv2022

An In-depth Study of Stochastic Backpropagation

In this paper, we provide an in-depth study of Stochastic Backpropagation (SBP) when training deep neural networks for standard image classification and object detection tasks. During backward propagation, SBP calculates the gradients by only using a subset of feature maps to save the GPU memory and computational cost. We interpret SBP as an efficient way to implement stochastic gradient decent by performing backpropagation dropout, which leads to considerable memory saving and training process speedup, with a minimal impact on the overall model accuracy. We offer some good practices to apply SBP in training image recognition models, which can be adopted in learning a wide range of deep neural networks. Experiments on image classification and object detection show that SBP can save up to 40% of GPU memory with less than 1% accuracy degradation.

cs.CV↗

arXiv2022

New MDS Entanglement-Assisted Quantum Codes from MDS Hermitian Self-Orthogonal Codes

The intersection ${\bf C}\bigcap {\bf C}^{\perp_H}$ of a linear code ${\bf C} \subset {\bf F}_{q^2}$ and its Hermitian dual ${\bf C}^{\perp_H}$ is called the Hermitian hull of this code. A linear code ${\bf C} \subset {\bf F}_{q^2}$ satisfying ${\bf C} \subset {\bf C}^{\perp_H}$ is called Hermitian self-orthogonal. Many Hermitian self-orthogonal codes were given for the construction of MDS quantum error correction codes (QECCs). In this paper we prove that for a nonnegative integer $h$ satisfying $0 \leq h \leq k$, a linear Hermitian self-orthogonal $[n, k]_{q^2}$ code is equivalent to a linear $h$-dimension Hermitian hull code. Therefore a lot of new MDS entanglement-assisted quantum error correction (EAQEC) codes can be constructed from previous known Hermitian self-orthogonal codes. Actually our method shows that previous constructed quantum MDS codes from Hermitian self-orthogonal codes can be transformed to MDS entanglement-assisted quantum codes with nonzero consumption parameter $c$ directly. We prove that MDS EAQEC $[[n, k, d, c]]_q$ codes with nonzero $c$ parameters and $d\leq \frac{n+2}{2}$ exist for arbitrary length $n \leq q^2+1$. Moreover any QECC constructed from $k$-dimensional Hermitian self-orthogonal codes can be transformed to $k$ different EAQEC codes.

cs.IT↗

arXiv2022

Artificial Intelligence Models for Cell Type and Subtype Identification Based on Single-Cell RNA Sequencing Data in Vision Science

Single-cell RNA sequencing (scRNA-seq) provides a high throughput, quantitative and unbiased framework for scientists in many research fields to identify and characterize cell types within heterogeneous cell populations from various tissues. However, scRNA-seq based identification of discrete cell-types is still labor intensive and depends on prior molecular knowledge. Artificial intelligence has provided faster, more accurate, and user-friendly approaches for cell-type identification. In this review, we discuss recent advances in cell-type identification methods using artificial intelligence techniques based on single-cell and single-nucleus RNA sequencing data in vision science.

q-bio.QM↗

arXiv2022

GPatch: Patching Graph Neural Networks for Cold-Start Recommendations

Cold start is an essential and persistent problem in recommender systems. State-of-the-art solutions rely on training hybrid models for both cold-start and existing users/items, based on the auxiliary information. Such a hybrid model would compromise the performance of existing users/items, which might make these solutions not applicable in real-worlds recommender systems where the experience of existing users/items must be guaranteed. Meanwhile, graph neural networks (GNNs) have been demonstrated to perform effectively warm (non-cold-start) recommendations. However, they have never been applied to handle the cold-start problem in a user-item bipartite graph. This is a challenging but rewarding task since cold-start users/items do not have links. Besides, it is nontrivial to design an appropriate GNN to conduct cold-start recommendations while maintaining the performance for existing users/items. To bridge the gap, we propose a tailored GNN-based framework (GPatch) that contains two separate but correlated components. First, an efficient GNN architecture -- GWarmer, is designed to model the warm users/items. Second, we construct correlated Patching Networks to simulate and patch GWarmer by conducting cold-start recommendations. Experiments on benchmark and large-scale commercial datasets demonstrate that GPatch is significantly superior in providing recommendations for both existing and cold-start users/items.

cs.IR↗