arXiv subjects

Ming Ding

Publications and source records attributed to Ming Ding.

At least 127 records · Page 7Linked to original sources

arXiv2022

A Roadmap for Big Model

With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields. At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research. In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application. We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.

cs.LG↗

arXiv2022

5G-Enabled Pseudonymity for Cooperative Intelligent Transportation System

Cooperative Intelligent Transportation Systems (C-ITS) enable communications between vehicles, road-side infrastructures, and road-users to improve users' safety and to efficiently manage traffic. Most, if not all, of the intelligent vehicles-to-everything (V2X) applications, often rely on continuous collection and sharing of sensitive information such as detailed location information which raises privacy concerns. In this light, a common approach to concealing the long-term identity of C-ITS vehicles is using multiple temporary identifiers, called pseudonyms. However, the legacy pseudonyms management approach is prone to linking attacks. The introduction of 5G network to V2X offers enhanced location accuracy, better clock synchronisation, improved modular service-based architecture, and enhanced security and privacy preservation controls. Motivated by the above enhancements, we study 5G-enabled pseudonyms for protecting vehicle identity privacy in C-ITS. We highlight the gaps in the current standards of pseudonyms management. We further provide recommendations regarding the pseudonyms management life-cycle.

cs.NI↗

arXiv2022

GLM: General Language Model Pretraining with Autoregressive Blank Infilling

There have been various types of pretraining architectures including autoencoding models (e.g., BERT), autoregressive models (e.g., GPT), and encoder-decoder models (e.g., T5). However, none of the pretraining frameworks performs the best for all tasks of three main categories including natural language understanding (NLU), unconditional generation, and conditional generation. We propose a General Language Model (GLM) based on autoregressive blank infilling to address this challenge. GLM improves blank filling pretraining by adding 2D positional encodings and allowing an arbitrary order to predict spans, which results in performance gains over BERT and T5 on NLU tasks. Meanwhile, GLM can be pretrained for different types of tasks by varying the number and lengths of blanks. On a wide range of tasks across NLU, conditional and unconditional generation, GLM outperforms BERT, T5, and GPT given the same model sizes and data, and achieves the best performance from a single pretrained model with 1.25x parameters of BERT Large , demonstrating its generalizability to different downstream tasks.

cs.CL↗

arXiv2022

FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding

The few-shot natural language understanding (NLU) task has attracted much recent attention. However, prior methods have been evaluated under a disparate set of protocols, which hinders fair comparison and measuring progress of the field. To address this issue, we introduce an evaluation framework that improves previous evaluation procedures in three key aspects, i.e., test performance, dev-test correlation, and stability. Under this new evaluation framework, we re-evaluate several state-of-the-art few-shot methods for NLU tasks. Our framework reveals new insights: (1) both the absolute performance and relative gap of the methods were not accurately estimated in prior literature; (2) no single method dominates most tasks with consistent performance; (3) improvements of some methods diminish with a larger pretrained model; and (4) gains from different methods are often complementary and the best combined model performs close to a strong fully-supervised baseline. We open-source our toolkit, FewNLU, that implements our evaluation framework along with a number of state-of-the-art methods.

cs.CL↗

arXiv2022

Generalized quantum cluster algebras: the Laurent phenomenon and upper bounds

Generalized quantum cluster algebras introduced in [1] are quantum deformation of generalized cluster algebras of geometric types. In this paper, we prove that the Laurent phenomenon holds in these generalized quantum cluster algebras. We also show that upper bounds coincide with the corresponding generalized quantum upper cluster algebras under the "coprimality" condition.

math.QA↗

arXiv2022

M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers

Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, M6-UFC, to unify any number of multi-modal controls. In M6-UFC, both the diverse control signals and the synthesized image are uniformly represented as a sequence of discrete tokens to be processed by Transformer. Different from existing two-stage autoregressive approaches such as DALL-E and VQGAN, M6-UFC adopts non-autoregressive generation (NAR) at the second stage to enhance the holistic consistency of the synthesized image, to support preserving specified image blocks, and to improve the synthesis speed. Further, we design a progressive algorithm that iteratively improves the non-autoregressively generated image, with the help of two estimators developed for evaluating the compliance with the controls and evaluating the fidelity of the synthesized image, respectively. Extensive experiments on a newly collected large-scale clothing dataset M2C-Fashion and a facial dataset Multi-Modal CelebA-HQ verify that M6-UFC can synthesize high-fidelity images that comply with flexible multi-modal controls.

cs.CV↗

arXiv2022

Hardness Results for Laplacians of Simplicial Complexes via Sparse-Linear Equation Complete Gadgets

We study linear equations in combinatorial Laplacians of $k$-dimensional simplicial complexes ($k$-complexes), a natural generalization of graph Laplacians. Combinatorial Laplacians play a crucial role in homology and are a central tool in topology. Beyond this, they have various applications in data analysis and physical modeling problems. It is known that nearly-linear time solvers exist for graph Laplacians. However, nearly-linear time solvers for combinatorial Laplacians are only known for restricted classes of complexes. This paper shows that linear equations in combinatorial Laplacians of 2-complexes are as hard to solve as general linear equations. More precisely, for any constant $c \geq 1$, if we can solve linear equations in combinatorial Laplacians of 2-complexes up to high accuracy in time $\tilde{O}((\# \text{ of nonzero coefficients})^c)$, then we can solve general linear equations with polynomially bounded integer coefficients and condition numbers up to high accuracy in time $\tilde{O}((\# \text{ of nonzero coefficients})^c)$. We prove this by a nearly-linear time reduction from general linear equations to combinatorial Laplacians of 2-complexes. Our reduction preserves the sparsity of the problem instances up to poly-logarithmic factors.

cs.CC↗

arXiv2022

Two-Commodity Flow is Equivalent to Linear Programming under Nearly-Linear Time Reductions

We give a nearly-linear time reduction that encodes any linear program as a 2-commodity flow problem with only a small blow-up in size. Under mild assumptions similar to those employed by modern fast solvers for linear programs, our reduction causes only a polylogarithmic multiplicative increase in the size of the program and runs in nearly-linear time. Our reduction applies to high-accuracy approximation algorithms and exact algorithms. Given an approximate solution to the 2-commodity flow problem, we can extract a solution to the linear program in linear time with only a polynomial factor increase in the error. This implies that any algorithm that solves the 2-commodity flow problem can solve linear programs in essentially the same time. Given a directed graph with edge capacities and two source-sink pairs, the goal of the 2-commodity flow problem is to maximize the sum of the flows routed between the two source-sink pairs subject to edge capacities and flow conservation. A 2-commodity flow can be directly written as a linear program, and thus we establish a nearly-tight equivalence between these two classes of problems. Our proof follows the outline of Itai's polynomial-time reduction of a linear program to a 2-commodity flow problem (JACM'78). Itai's reduction shows that exactly solving 2-commodity flow and exactly solving linear programming are polynomial-time equivalent. We improve Itai's reduction to nearly preserve the problem representation size in each step. In addition, we establish an error bound for approximately solving each intermediate problem in the reduction, and show that the accumulated error is polynomially bounded. We remark that our reduction does not run in strongly polynomial time and that it is open whether 2-commodity flow and linear programming are equivalent in strongly polynomial time.

cs.CC↗

arXiv2022

Negative-ResNet: Noisy Ambulatory Electrocardiogram Signal Classification Scheme

With recently successful applications of deep learning in computer vision and general signal processing, deep learning has shown many unique advantages in medical signal processing. However, data labelling quality has become one of the most significant issues for AI applications, especially when it requires domain knowledge (e.g. medical image labelling). In addition, there might be noisy labels in practical datasets, which might impair the training process of neural networks. In this work, we propose a semi-supervised algorithm for training data samples with noisy labels by performing selected Positive Learning (PL) and Negative Learning (NL). To verify the effectiveness of the proposed scheme, we designed a portable ECG patch -- iRealCare -- and applied the algorithm on a real-life dataset. Our experimental results show that we can achieve an accuracy of 91.0 %, which is 6.2 % higher than a normal training process with ResNet. There are 65 patients in our dataset and we randomly picked 2 patients to perform validation.

eess.SP↗

arXiv2022

A Wearable ECG Monitor for Deep Learning Based Real-Time Cardiovascular Disease Detection

Cardiovascular disease has become one of the most significant threats endangering human life and health. Recently, Electrocardiogram (ECG) monitoring has been transformed into remote cardiac monitoring by Holter surveillance. However, the widely used Holter can bring a great deal of discomfort and inconvenience to the individuals who carry them. We developed a new wireless ECG patch in this work and applied a deep learning framework based on the Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) models. However, we find that the models using the existing techniques are not able to differentiate two main heartbeat types (Supraventricular premature beat and Atrial fibrillation) in our newly obtained dataset, resulting in low accuracy of 58.0 %. We proposed a semi-supervised method to process the badly labelled data samples with using the confidence-level-based training. The experiment results conclude that the proposed method can approach an average accuracy of 90.2 %, i.e., 5.4 % higher than the accuracy of conventional ECG classification methods.

eess.SP↗

arXiv2022

Path Planning for the Dynamic UAV-Aided Wireless Systems using Monte Carlo Tree Search

For UAV-aided wireless systems, online path planning attracts much attention recently. To better adapt to the real-time dynamic environment, we, for the first time, propose a Monte Carlo Tree Search (MCTS)-based path planning scheme. In details, we consider a single UAV acts as a mobile server to provide computation tasks offloading services for a set of mobile users on the ground, where the movement of ground users follows a Random Way Point model. Our model aims at maximizing the average throughput under energy consumption and user fairness constraints, and the proposed timesaving MCTS algorithm can further improve the performance. Simulation results show that the proposed algorithm achieves a larger average throughput and a faster convergence performance compared with the baseline algorithms of Q-learning and Deep Q-Network.

cs.NI↗

arXiv2021

Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks

Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements. In this work, we present a systematical reproduction of 12 recent HGNNs by using their official codes, datasets, settings, and hyperparameters, revealing surprising findings about the progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN and GAT, are largely underestimated due to improper settings. GAT with proper inputs can generally match or outperform all existing HGNNs across various scenarios. To facilitate robust and reproducible HGNN research, we construct the Heterogeneous Graph Benchmark (HGB), consisting of 11 diverse datasets with three tasks. HGB standardizes the process of heterogeneous graph data splits, feature processing, and performance evaluation. Finally, we introduce a simple but very strong baseline Simple-HGN--which significantly outperforms all previous models on HGB--to accelerate the advancement of HGNNs in the future.

cs.LG↗

arXiv2021

The cluster multiplication theorem for acyclic quantum cluster algebras

Let $Q$ be a finite acyclic valued quiver. We give the cluster multiplication formulas in the quantum cluster algebra of $Q$ with arbitrary coefficients, by applying certain quotients of derived Hall subalgebras of $Q$. These formulas can be viewed as the quantum version of the cluster multiplication theorem in the classical cluster algebra proved by Caldero-Keller for finite type, Hubery for affine type and Xiao-Xu for acyclic quivers.

math.RT↗

arXiv2021

Federated Learning for Smart Healthcare: A Survey

Recent advances in communication technologies and Internet-of-Medical-Things have transformed smart healthcare enabled by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and processing that may be infeasible in realistic healthcare scenarios due to the high scalability of modern healthcare networks and growing data privacy concerns. Federated Learning (FL), as an emerging distributed collaborative AI paradigm, is particularly attractive for smart healthcare, by coordinating multiple clients (e.g., hospitals) to perform AI training without sharing raw data. Accordingly, we provide a comprehensive survey on the use of FL in smart healthcare. First, we present the recent advances in FL, the motivations, and the requirements of using FL in smart healthcare. The recent FL designs for smart healthcare are then discussed, ranging from resource-aware FL, secure and privacy-aware FL to incentive FL and personalized FL. Subsequently, we provide a state-of-the-art review on the emerging applications of FL in key healthcare domains, including health data management, remote health monitoring, medical imaging, and COVID-19 detection. Several recent FL-based smart healthcare projects are analyzed, and the key lessons learned from the survey are also highlighted. Finally, we discuss interesting research challenges and possible directions for future FL research in smart healthcare.

cs.LG↗

arXiv2021

Controllable Generation from Pre-trained Language Models via Inverse Prompting

Large-scale pre-trained language models have demonstrated strong capabilities of generating realistic text. However, it remains challenging to control the generation results. Previous approaches such as prompting are far from sufficient, which limits the usage of language models. To tackle this challenge, we propose an innovative method, inverse prompting, to better control text generation. The core idea of inverse prompting is to use generated text to inversely predict the prompt during beam search, which enhances the relevance between the prompt and the generated text and provides better controllability. Empirically, we pre-train a large-scale Chinese language model to perform a systematic study using human evaluation on the tasks of open-domain poem generation and open-domain long-form question answering. Our results show that our proposed method substantially outperforms the baselines and that our generation quality is close to human performance on some of the tasks. Narrators can try our poem generation demo at https://pretrain.aminer.cn/apps/poetry.html, while our QA demo can be found at https://pretrain.aminer.cn/app/qa. For researchers, the code is provided in https://github.com/THUDM/InversePrompting.

cs.CL↗

arXiv2021

CogView: Mastering Text-to-Image Generation via Transformers

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.

cs.CV↗

arXiv2021

Federated Learning for COVID-19 Detection with Generative Adversarial Networks in Edge Cloud Computing

COVID-19 has spread rapidly across the globe and become a deadly pandemic. Recently, many artificial intelligence-based approaches have been used for COVID-19 detection, but they often require public data sharing with cloud datacentres and thus remain privacy concerns. This paper proposes a new federated learning scheme, called FedGAN, to generate realistic COVID-19 images for facilitating privacy-enhanced COVID-19 detection with generative adversarial networks (GANs) in edge cloud computing. Particularly, we first propose a GAN where a discriminator and a generator based on convolutional neural networks (CNNs) at each edge-based medical institution alternatively are trained to mimic the real COVID-19 data distribution. Then, we propose a new federated learning solution which allows local GANs to collaborate and exchange learned parameters with a cloud server, aiming to enrich the global GAN model for generating realistic COVID-19 images without the need for sharing actual data. To enhance the privacy in federated COVID-19 data analytics, we integrate a differential privacy solution at each hospital institution. Moreover, we propose a new blockchain-based FedGAN framework for secure COVID-19 data analytics, by decentralizing the FL process with a new mining solution for low running latency. Simulations results demonstrate the superiority of our approach for COVID-19 detection over the state-of-the-art schemes.

eess.SP↗

arXiv2021

Cooperative Task Offloading and Block Mining in Blockchain-based Edge Computing with Multi-agent Deep Reinforcement Learning

The convergence of mobile edge computing (MEC) and blockchain is transforming the current computing services in mobile networks, by offering task offloading solutions with security enhancement empowered by blockchain mining. Nevertheless, these important enabling technologies have been studied separately in most existing works. This article proposes a novel cooperative task offloading and block mining (TOBM) scheme for a blockchain-based MEC system where each edge device not only handles data tasks but also deals with block mining for improving the system utility. To address the latency issues caused by the blockchain operation in MEC, we develop a new Proof-of-Reputation consensus mechanism based on a lightweight block verification strategy. A multi-objective function is then formulated to maximize the system utility of the blockchain-based MEC system, by jointly optimizing offloading decision, channel selection, transmit power allocation, and computational resource allocation. We propose a novel distributed deep reinforcement learning-based approach by using a multi-agent deep deterministic policy gradient algorithm. We then develop a game-theoretic solution to model the offloading and mining competition among edge devices as a potential game, and prove the existence of a pure Nash equilibrium. Simulation results demonstrate the significant system utility improvements of our proposed scheme over baseline approaches.

eess.SP↗