Searcharxiv⌕ Search

arXiv subjects

Liang Zhao

Publications and source records attributed to Liang Zhao.

At least 307 records · Page 17Linked to original sources
arXiv2023

TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition

Few-shot named entity recognition (NER) exploits limited annotated instances to identify named mentions. Effectively transferring the internal or external resources thus becomes the key to few-shot NER. While the existing prompt tuning methods have shown remarkable few-shot performances, they still fail to make full use of knowledge. In this work, we investigate the integration of rich knowledge to prompt tuning for stronger few-shot NER. We propose incorporating the deep prompt tuning framework with threefold knowledge (namely TKDP), including the internal 1) context knowledge and the external 2) label knowledge & 3) sememe knowledge. TKDP encodes the three feature sources and incorporates them into the soft prompt embeddings, which are further injected into an existing pre-trained language model to facilitate predictions. On five benchmark datasets, our knowledge-enriched model boosts by at most 11.53% F1 over the raw deep prompt method, and significantly outperforms 8 strong-performing baseline systems in 5-/10-/20-shot settings, showing great potential in few-shot NER. Our TKDP can be broadly adapted to other few-shot tasks without effort.

cs.CL↗
arXiv2023

JGAT: a joint spatio-temporal graph attention model for brain decoding

The decoding of brain neural networks has been an intriguing topic in neuroscience for a well-rounded understanding of different types of brain disorders and cognitive stimuli. Integrating different types of connectivity, e.g., Functional Connectivity (FC) and Structural Connectivity (SC), from multi-modal imaging techniques can take their complementary information into account and therefore have the potential to get better decoding capability. However, traditional approaches for integrating FC and SC overlook the dynamical variations, which stand a great chance to over-generalize the brain neural network. In this paper, we propose a Joint kernel Graph Attention Network (JGAT), which is a new multi-modal temporal graph attention network framework. It integrates the data from functional Magnetic Resonance Images (fMRI) and Diffusion Weighted Imaging (DWI) while preserving the dynamic information at the same time. We conduct brain-decoding tasks with our JGAT on four independent datasets: three of 7T fMRI datasets from the Human Connectome Project (HCP) and one from animal neural recordings. Furthermore, with Attention Scores (AS) and Frame Scores (FS) computed and learned from the model, we can locate several informative temporal segments and build meaningful dynamical pathways along the temporal domain for the HCP datasets. The URL to the code of JGAT model: https://github.com/BRAINML-GT/JGAT.

q-bio.NC↗
arXiv2023

Graph Neural Network for spatiotemporal data: methods and applications

In the era of big data, there has been a surge in the availability of data containing rich spatial and temporal information, offering valuable insights into dynamic systems and processes for applications such as weather forecasting, natural disaster management, intelligent transport systems, and precision agriculture. Graph neural networks (GNNs) have emerged as a powerful tool for modeling and understanding data with dependencies to each other such as spatial and temporal dependencies. There is a large amount of existing work that focuses on addressing the complex spatial and temporal dependencies in spatiotemporal data using GNNs. However, the strong interdisciplinary nature of spatiotemporal data has created numerous GNNs variants specifically designed for distinct application domains. Although the techniques are generally applicable across various domains, cross-referencing these methods remains essential yet challenging due to the absence of a comprehensive literature review on GNNs for spatiotemporal data. This article aims to provide a systematic and comprehensive overview of the technologies and applications of GNNs in the spatiotemporal domain. First, the ways of constructing graphs from spatiotemporal data are summarized to help domain experts understand how to generate graphs from various types of spatiotemporal data. Then, a systematic categorization and summary of existing spatiotemporal GNNs are presented to enable domain experts to identify suitable techniques and to support model developers in advancing their research. Moreover, a comprehensive overview of significant applications in the spatiotemporal domain is offered to introduce a broader range of applications to model developers and domain experts, assisting them in exploring potential research topics and enhancing the impact of their work. Finally, open challenges and future directions are discussed.

cs.LG↗
arXiv2023

Domain Generalization Deep Graph Transformation

Graph transformation that predicts graph transition from one mode to another is an important and common problem. Despite much progress in developing advanced graph transformation techniques in recent years, the fundamental assumption typically required in machine-learning models that the testing and training data preserve the same distribution does not always hold. As a result, domain generalization graph transformation that predicts graphs not available in the training data is under-explored, with multiple key challenges to be addressed including (1) the extreme space complexity when training on all input-output mode combinations, (2) difference of graph topologies between the input and the output modes, and (3) how to generalize the model to (unseen) target domains that are not in the training data. To fill the gap, we propose a multi-input, multi-output, hypernetwork-based graph neural network (MultiHyperGNN) that employs a encoder and a decoder to encode topologies of both input and output modes and semi-supervised link prediction to enhance the graph transformation task. Instead of training on all mode combinations, MultiHyperGNN preserves a constant space complexity with the encoder and the decoder produced by two novel hypernetworks. Comprehensive experiments show that MultiHyperGNN has a superior performance than competing models in both prediction and domain generalization tasks.

cs.LG↗
arXiv2023

Standardizing Representation for Equality with a Population Seat Index

Proportional representation (PR) has long been believed the ideal system for the equality of individuals in apportioning the seats of a legislature body to subgroups. We observe that PR implicitly assumes the (standard) number of representatives is proportional to the population, a situation no longer observed since 1820s. To address this issue, we suggest to formulate the apportionment problem in a broader context by explicitly specifying a standard function $f$ such that $f(p)$ is the standard, possibly fractional number of representatives for population $p$, where PR assumes $f(p)\propto p$. For this generalized apportionment problem, we give a population seat index (PSI) $\frac{f^{-1}(s)}{p}$ for quantifying the contribution of an individual in assigning $s$ seats to a population $p$, where $f^{-1}$ is the inverse of $f$. With the PSI, we derive apportioning schemes with absolute and relative individual equality. Particularly, for $s$ seats, populations $p_1, \ldots, p_k$, and a standard function $f(p) = a + b p^γ$ with constants $a, b, γ\ge 0$, the ideal, possibly fractional number of seats for subgroup $i$ is $a + \frac{(S-ka)p_i^γ}{\sum p_j^γ}$, not $\frac{Sp_i}{\sum p_j}$ calculated by PR which works only for $a=0$, $γ=1$. Finally, since real-world observations indicate a standard function $f \propto p^γ$ with $γ< 1$, we conclude that PR represents individuals in less populous subgroups less than individuals in more populous subgroups.

physics.soc-ph↗
arXiv2023

Deep Graph Representation Learning and Optimization for Influence Maximization

Influence maximization (IM) is formulated as selecting a set of initial users from a social network to maximize the expected number of influenced users. Researchers have made great progress in designing various traditional methods, and their theoretical design and performance gain are close to a limit. In the past few years, learning-based IM methods have emerged to achieve stronger generalization ability to unknown graphs than traditional ones. However, the development of learning-based IM methods is still limited by fundamental obstacles, including 1) the difficulty of effectively solving the objective function; 2) the difficulty of characterizing the diversified underlying diffusion patterns; and 3) the difficulty of adapting the solution under various node-centrality-constrained IM variants. To cope with the above challenges, we design a novel framework DeepIM to generatively characterize the latent representation of seed sets, and we propose to learn the diversified information diffusion pattern in a data-driven and end-to-end manner. Finally, we design a novel objective function to infer optimal seed sets under flexible node-centrality-based budget constraints. Extensive analyses are conducted over both synthetic and real-world datasets to demonstrate the overall performance of DeepIM. The code and data are available at: https://github.com/triplej0079/DeepIM.

cs.SI↗
arXiv2023

Molecular Design Based on Integer Programming and Splitting Data Sets by Hyperplanes

A novel framework for designing the molecular structure of chemical compounds with a desired chemical property has recently been proposed. The framework infers a desired chemical graph by solving a mixed integer linear program (MILP) that simulates the computation process of a feature function defined by a two-layered model on chemical graphs and a prediction function constructed by a machine learning method. To improve the learning performance of prediction functions in the framework, we design a method that splits a given data set $\mathcal{C}$ into two subsets $\mathcal{C}^{(i)},i=1,2$ by a hyperplane in a chemical space so that most compounds in the first (resp., second) subset have observed values lower (resp., higher) than a threshold $θ$. We construct a prediction function $ψ$ to the data set $\mathcal{C}$ by combining prediction functions $ψ_i,i=1,2$ each of which is constructed on $\mathcal{C}^{(i)}$ independently. The results of our computational experiments suggest that the proposed method improved the learning performance for several chemical properties to which a good prediction function has been difficult to construct.

cs.CE↗
arXiv2023

Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillation

Federated Learning has gained popularity among medical institutions since it enables collaborative training between clients (e.g., hospitals) without aggregating data. However, due to the high cost associated with creating annotations, especially for large 3D image datasets, clinical institutions do not have enough supervised data for training locally. Thus, the performance of the collaborative model is subpar under limited supervision. On the other hand, large institutions have the resources to compile data repositories with high-resolution images and labels. Therefore, individual clients can utilize the knowledge acquired in the public data repositories to mitigate the shortage of private annotated images. In this paper, we propose a federated few-shot learning method with dual knowledge distillation. This method allows joint training with limited annotations across clients without jeopardizing privacy. The supervised learning of the proposed method extracts features from limited labeled data in each client, while the unsupervised data is used to distill both feature and response-based knowledge from a national data repository to further improve the accuracy of the collaborative model and reduce the communication cost. Extensive evaluations are conducted on 3D magnetic resonance knee images from a private clinical dataset. Our proposed method shows superior performance and less training time than other semi-supervised federated learning methods. Codes and additional visualization results are available at https://github.com/hexiaoxiao-cs/fedml-knee.

eess.IV↗
arXiv2023

Privacy-Enhancing Technologies in Federated Learning for the Internet of Healthcare Things: A Survey

Advancements in wearable medical devices in IoT technology are shaping the modern healthcare system. With the emergence of the Internet of Healthcare Things (IoHT), we are witnessing how efficient healthcare services are provided to patients and how healthcare professionals are effectively used AI-based models to analyze the data collected from IoHT devices for the treatment of various diseases. To avoid privacy breaches, these data must be processed and analyzed in compliance with the legal rules and regulations such as HIPAA and GDPR. Federated learning is a machine leaning based approach that allows multiple entities to collaboratively train a ML model without sharing their data. This is particularly useful in the healthcare domain where data privacy and security are big concerns. Even though FL addresses some privacy concerns, there is still no formal proof of privacy guarantees for IoHT data. Privacy Enhancing Technologies (PETs) are a set of tools and techniques that are designed to enhance the privacy and security of online communications and data sharing. PETs provide a range of features that help protect users' personal information and sensitive data from unauthorized access and tracking. This paper reviews PETs in detail and comprehensively in relation to FL in the IoHT setting and identifies several key challenges for future research.

cs.NI↗
arXiv2023

Limit distribution of partial transposition of block random matrices

It is well known that, under some assumptions, the limit distribution of random block matrices and their partial transposition converges to the distributions of random variables in some noncommutative probability space. Using free probability theory, we obtain the relation between the free cumulants of the corresponding random variables. As an application, we are able to derive a new family of co-completely positive and k-positive maps by using the Wishart ensemble.

quant-ph↗
arXiv2023

Unexpectedly Spontaneous Water Dissociation on Graphene Oxide Supported by Copper Substrate

Water dissociation is of fundamental importance in scientific fields and has drawn considerable interest in diverse technological applications. However, the high activation barrier of breaking the O-H bond within the water molecule has been identified as the bottleneck, even for the water adsorbed on the graphene oxide (GO). Herein, using the density functional theory calculations, we demonstrate that the water molecule can be spontaneously dissociated on GO supported by the (111) surface of the copper substrate (Copper-GO). This process involves a proton transferring from water to the interfacial oxygen group, and a hydroxide covalently bonding to GO. Compared to that on GO, the water dissociation barrier on Copper-GO is significantly decreased to be less than or comparable to thermal fluctuations. This is ascribed to the orbital-hybridizing interaction between copper substrate and GO, which enhances the reaction activity of interfacial oxygen groups along the basal plane of GO for water dissociation. Our work provides a novel strategy to access water dissociation via the substrate-enhanced reaction activity of interfacial oxygen groups on GO and indicates that the substrate can serve as an essential key to tuning the catalytic performance of various two-dimensional material devices.

cond-mat.mtrl-sci↗
arXiv2023

Normalized solutions for nonlinear Schrödinger equations on graphs

We are concerned with the nonlinear Schrödinger equation with an $L^2$ mass constraint on both finite and locally finite graphs and prove that the equation has a normalized solution by employing variational methods. We also pay attention to the behaviours of the normalized solution as the mass constraint tends to $0^+$ or $+\infty$ and give clear descriptions of the limit equations. Finally, we provide some numerical experiments on a finite graph to illustrate our theoretical results.

math.AP↗
arXiv2023

Locally Spontaneous Dynamic Oxygen Migration on Biphenylene: A DFT Study

The dynamic oxygen migration at the interface of carbon allotropes dominated by the periodic hexagonal rings, including graphene and carbon nanotube, has opened up a new avenue to realize dynamic covalent materials. However, for the carbon materials with hybrid carbon rings, such as biphenylene, whether the dynamic oxygen migration at its interface can still be found remains unknown. Using both density functional theory calculations and machine-learning-based molecular dynamics (MLMD) simulations, we found that the oxygen migration departing away from the four-membered carbon (C4) ring is hindered, and the oxygen atom prefers to spontaneously migrate toward/around the C4 ring. This locally spontaneous dynamic oxygen migration on the biphenylene is attributed to the high barrier of about 1.5 eV for the former process and relatively low barrier of about 0.3 eV for the latter one, originating from the enhanced activity of C-O bond near/around the C4 ring due to the hybrid carbon rings structure. Moreover, the locally spontaneous dynamic oxygen migration is further confirmed by MLMD simulations. This work sheds light on the potential of biphenylene as a catalyst for spatial-controlled energy conversion and provides the guidance for realizing the dynamic covalent interface at other carbon-based or two-dimensional materials.

cond-mat.mtrl-sci↗
arXiv2023

Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks

Temporal domain generalization is a promising yet extremely challenging area where the goal is to learn models under temporally changing data distributions and generalize to unseen data distributions following the trends of the change. The advancement of this area is challenged by: 1) characterizing data distribution drift and its impacts on models, 2) expressiveness in tracking the model dynamics, and 3) theoretical guarantee on the performance. To address them, we propose a Temporal Domain Generalization with Drift-Aware Dynamic Neural Network (DRAIN) framework. Specifically, we formulate the problem into a Bayesian framework that jointly models the relation between data and model dynamics. We then build a recurrent graph generation scenario to characterize the dynamic graph-structured neural networks learned across different time points. It captures the temporal drift of model parameters and data distributions and can predict models in the future without the presence of future data. In addition, we explore theoretical guarantees of the model performance under the challenging temporal DG setting and provide theoretical analysis, including uncertainty and generalization error. Finally, extensive experiments on several real-world benchmarks with temporal drift demonstrate the effectiveness and efficiency of the proposed method.

cs.LG↗
arXiv2023

Knowledge-enhanced Neural Machine Reasoning: A Review

Knowledge-enhanced neural machine reasoning has garnered significant attention as a cutting-edge yet challenging research area with numerous practical applications. Over the past few years, plenty of studies have leveraged various forms of external knowledge to augment the reasoning capabilities of deep models, tackling challenges such as effective knowledge integration, implicit knowledge mining, and problems of tractability and optimization. However, there is a dearth of a comprehensive technical review of the existing knowledge-enhanced reasoning techniques across the diverse range of application domains. This survey provides an in-depth examination of recent advancements in the field, introducing a novel taxonomy that categorizes existing knowledge-enhanced methods into two primary categories and four subcategories. We systematically discuss these methods and highlight their correlations, strengths, and limitations. Finally, we elucidate the current application domains and provide insight into promising prospects for future research.

cs.AI↗
arXiv2022

Deep Spatial Domain Generalization

Spatial autocorrelation and spatial heterogeneity widely exist in spatial data, which make the traditional machine learning model perform badly. Spatial domain generalization is a spatial extension of domain generalization, which can generalize to unseen spatial domains in continuous 2D space. Specifically, it learns a model under varying data distributions that generalizes to unseen domains. Although tremendous success has been achieved in domain generalization, there exist very few works on spatial domain generalization. The advancement of this area is challenged by: 1) Difficulty in characterizing spatial heterogeneity, and 2) Difficulty in obtaining predictive models for unseen locations without training data. To address these challenges, this paper proposes a generic framework for spatial domain generalization. Specifically, We develop the spatial interpolation graph neural network that handles spatial data as a graph and learns the spatial embedding on each node and their relationships. The spatial interpolation graph neural network infers the spatial embedding of an unseen location during the test phase. Then the spatial embedding of the target location is used to decode the parameters of the downstream-task model directly on the target location. Finally, extensive experiments on thirteen real-world datasets demonstrate the proposed method's strength.

cs.LG↗
arXiv2022

Saliency-Augmented Memory Completion for Continual Learning

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, how to forget is a problem continual learning must address. Therefore, beyond simply avoiding catastrophic forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1. storage efficiency, 2. generalizability, and 3. some interpretability. To achieve these simultaneously, our paper proposes a new saliency-augmented memory completion framework for continual learning, inspired by recent discoveries in memory completion separation in cognitive neuroscience. Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding. When learning new tasks, previous data from memory are inpainted by an adaptive data generation module, which is inspired by how humans complete episodic memory. The module's parameters are shared across all tasks and it can be jointly trained with a continual learning classifier as bilevel optimization. Extensive experiments on several continual learning and image classification benchmarks demonstrate the proposed method's effectiveness and efficiency.

cs.LG↗
arXiv2022

Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning

As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing DNNs become more complex and diverse, ranging from improving a conventional model accuracy metric to infusing advanced human virtues such as fairness, accountability, transparency (FaccT), and unbiasedness. Recently, techniques in Explainable Artificial Intelligence (XAI) are attracting considerable attention, and have tremendously helped Machine Learning (ML) engineers in understanding AI models. However, at the same time, we started to witness the emerging need beyond XAI among AI communities; based on the insights learned from XAI, how can we better empower ML engineers in steering their DNNs so that the model's reasonableness and performance can be improved as intended? This article provides a timely and extensive literature overview of the field Explanation-Guided Learning (EGL), a domain of techniques that steer the DNNs' reasoning process by adding regularization, supervision, or intervention on model explanations. In doing so, we first provide a formal definition of EGL and its general learning paradigm. Secondly, an overview of the key factors for EGL evaluation, as well as summarization and categorization of existing evaluation procedures and metrics for EGL are provided. Finally, the current and potential future application areas and directions of EGL are discussed, and an extensive experimental study is presented aiming at providing comprehensive comparative studies among existing EGL models in various popular application domains, such as Computer Vision (CV) and Natural Language Processing (NLP) domains.

cs.AI↗