arXiv subjects

Dan Liu

Publications and source records attributed to Dan Liu.

At least 37 records · Page 2Linked to original sources

arXiv2025

On the number of subgroups of the group $\mathbb{Z}_{m_{1}} \times \mathbb{Z}_{m_{2}}$ with $m_{1}m_{2}\leq x$ such that $m_{1}m_{2}$ is a $k$-th power

Let ${\Bbb Z}_{m}$ be the additive group of residue classes modulo $m$ and $s(m_{1},m_{2})$ denote the number of subgroups of the group ${\Bbb Z}_{m_{1}}\times {\Bbb Z}_{m_{2}}$, where $m_{1}$ and $m_{2}$ are arbitrary positive integers. We consider sums of type $\sum\limits_{\substack{m_{1}m_{2}\leq x \\ m_{1}m_{2}\in N_{k}}}s(m_{1},m_{2})$, where $N_{k}$ is the set of $k$-th power of natural numbers. In particular, we deduce asymptotic formulas with $k=2$ and $k=3$.

math.NT↗

arXiv2025

Synthetic Data Generation for Augmenting Small Samples

Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases sample size and is seen as a form of regularization that increases the diversity of small datasets, leading them to perform better on unseen data. We found that augmentation improves prognostic performance for datasets that: have fewer observations, with smaller baseline AUC, have higher cardinality categorical variables, and have more balanced outcome variables. No specific generative model consistently outperformed the others. We developed a decision support model that can be used to inform analysts if augmentation would be useful. For seven small application datasets, augmenting the existing data results in an increase in AUC between 4.31% (AUC from 0.71 to 0.75) and 43.23% (AUC from 0.51 to 0.73), with an average 15.55% relative improvement, demonstrating the nontrivial impact of augmentation on small datasets (p=0.0078). Augmentation AUC was higher than resampling only AUC (p=0.016). The diversity of augmented datasets was higher than the diversity of resampled datasets (p=0.046).

cs.LG↗

arXiv2024

Exotic properties and manipulation in 2D semimetal Mn2B2(OH)2: a theoretical study

Most functional materials possess one single outstanding property and are limited to be used for a particular purpose. Instead of integrating materials with different functions into one module, designing materials with controllable multi-functions is more promising for the electronic industry. In this study, we investigate an unexplored alpha-phase of two-dimensional (2D) Mn2B2(OH)2 theoretically. Eighteen distinct electrical polarizations, characterized by three different magnitudes and twelve different directions, are found in this phase. The switch of the electrical polarizations is also linked to an observed splitting of band structures between different spin states and the ferroelasticity of the system. The manipulation of these properties can be realized through controlling the alignment of Mn-OH-Mn chains. Additionally, the approximately honeycomb lattice for the atomic layer of boron indicate the potential superconductivity in the system. The diverse and tunable properties make the proposed material as an outstanding candidate for sensing applications at the 2D limit.

cond-mat.mtrl-sci↗

arXiv2024

Controllable Text Generation for Large Language Models: A Survey

In Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated high text generation quality. However, in real-world applications, LLMs must meet increasingly complex requirements. Beyond avoiding misleading or inappropriate content, LLMs are also expected to cater to specific user needs, such as imitating particular writing styles or generating text with poetic richness. These varied demands have driven the development of Controllable Text Generation (CTG) techniques, which ensure that outputs adhere to predefined control conditions--such as safety, sentiment, thematic consistency, and linguistic style--while maintaining high standards of helpfulness, fluency, and diversity. This paper systematically reviews the latest advancements in CTG for LLMs, offering a comprehensive definition of its core concepts and clarifying the requirements for control conditions and text quality. We categorize CTG tasks into two primary types: content control and attribute control. The key methods are discussed, including model retraining, fine-tuning, reinforcement learning, prompt engineering, latent space manipulation, and decoding-time intervention. We analyze each method's characteristics, advantages, and limitations, providing nuanced insights for achieving generation control. Additionally, we review CTG evaluation methods, summarize its applications across domains, and address key challenges in current research, including reduced fluency and practicality. We also propose several appeals, such as placing greater emphasis on real-world applications in future research. This paper aims to offer valuable guidance to researchers and developers in the field. Our reference list and Chinese version are open-sourced at https://github.com/IAAR-Shanghai/CTGSurvey.

cs.CL↗

arXiv2024

LiRank: Industrial Large Scale Ranking Models at LinkedIn

We present LiRank, a large-scale ranking framework at LinkedIn that brings to production state-of-the-art modeling architectures and optimization methods. We unveil several modeling improvements, including Residual DCN, which adds attention and residual connections to the famous DCNv2 architecture. We share insights into combining and tuning SOTA architectures to create a unified model, including Dense Gating, Transformers and Residual DCN. We also propose novel techniques for calibration and describe how we productionalized deep learning based explore/exploit methods. To enable effective, production-grade serving of large ranking models, we detail how to train and compress models using quantization and vocabulary compression. We provide details about the deployment setup for large-scale use cases of Feed ranking, Jobs Recommendations, and Ads click-through rate (CTR) prediction. We summarize our learnings from various A/B tests by elucidating the most effective technical approaches. These ideas have contributed to relative metrics improvements across the board at LinkedIn: +0.5% member sessions in the Feed, +1.76% qualified job applications for Jobs search and recommendations, and +4.3% for Ads CTR. We hope this work can provide practical insights and solutions for practitioners interested in leveraging large-scale deep ranking systems.

cs.LG↗

arXiv2024

Ferroelectricity in oxygen-terminated 2D carbides of lanthanide elements

We investigate the properties of oxygen-functionalized carbides of lanthanide elements with the composition M2CO2 (M=Gd, Tb,Dy) that form two-dimensional (2D) structures. Our ab initio calculations reveal that oxygen termination turns M2C monolayers into semiconductors with two dynamically stable phases. Of these, the energetically favored alpha-phase becomes ferroelectric, whereas the beta-phase turns anti-ferroelectric. Applying in-plane biaxial strain may transform one phase into the other, changes the ferroelectric polarization of the alpha-phase in a linear fashion, and modifies the size and nature of the fundamental band gap from direct to indirect. The structure with a direct band gap exhibits in-plane isotropic electronic and optical properties. This previously unexplored class of systems also exhibits excellent photon absorption in the ultraviolet range.

cond-mat.mtrl-sci↗

arXiv2024

Model Failure or Data Corruption? Exploring Inconsistencies in Building Energy Ratings with Self-Supervised Contrastive Learning

Building Energy Rating (BER) stands as a pivotal metric, enabling building owners, policymakers, and urban planners to understand the energy-saving potential through improving building energy efficiency. As such, enhancing buildings' BER levels is expected to directly contribute to the reduction of carbon emissions and promote climate improvement. Nonetheless, the BER assessment process is vulnerable to missing and inaccurate measurements. In this study, we introduce \texttt{CLEAR}, a data-driven approach designed to scrutinize the inconsistencies in BER assessments through self-supervised contrastive learning. We validated the effectiveness of \texttt{CLEAR} using a dataset representing Irish building stocks. Our experiments uncovered evidence of inconsistent BER assessments, highlighting measurement data corruption within this real-world dataset.

cs.LG↗

arXiv2024

LuminLab: An AI-Powered Building Retrofit and Energy Modelling Platform

This paper describes the technical and conceptual development of the LuminLab platform, an online tool that integrates a purpose-fit human-centric AI chatbot and predictive energy model into a streamlined front-end that can rapidly produce and discuss building retrofit plans in natural language. The platform provides users with the ability to engage with a range of possible retrofit pathways tailored to their individual budget and building needs on-demand. Given the complicated and costly nature of building retrofit projects, which rely on a variety of stakeholder groups with differing goals and incentives, we feel that AI-powered tools such as this have the potential to pragmatically de-silo knowledge, improve communication, and empower individual homeowners to undertake incremental retrofit projects that might not happen otherwise.

cs.HC↗

arXiv2024

Dynamic Treatment Regimes with Replicated Observations Available for Error-prone Covariates: a Q-learning Approach

Dynamic treatment regimes (DTRs) have received an increasing interest in recent years. DTRs are sequences of treatment decision rules tailored to patient-level information. The main goal of the DTR study is to identify an optimal DTR, a sequence of treatment decision rules that yields the best expected clinical outcome. Q-learning has been considered as one of the most popular regression-based methods to estimate the optimal DTR. However, it is rarely studied in an error-prone setting, where the patient information is contaminated with measurement error. In this paper, we study the effect of covariate measurement error on Q-learning and propose a correction method to correct the measurement error in Q-learning. Simulation studies are conducted to assess the performance of the proposed method in Q-learning. We illustrate the use of the proposed method in an application to the sequenced treatment alternatives to relieve depression data.

stat.ME↗

arXiv2024

Q-learning in Dynamic Treatment Regimes with Misclassified Binary Outcome

The study of precision medicine involves dynamic treatment regimes (DTRs), which are sequences of treatment decision rules recommended by taking patient-level information as input. The primary goal of the DTR study is to identify an optimal DTR, a sequence of treatment decision rules that leads to the best expected clinical outcome. Statistical methods have been developed in recent years to estimate an optimal DTR, including Q-learning, a regression-based method in the DTR literature. Although there are many studies concerning Q-learning, little attention has been given in the presence of noisy data, such as misclassified outcomes. In this paper, we investigate the effect of outcome misclassification on Q-learning and propose a correction method to accommodate the misclassification effect. Simulation studies are conducted to demonstrate the satisfactory performance of the proposed method. We illustrate the proposed method in two examples from the National Health and Nutrition Examination Survey Data I Epidemiologic Follow-up Study and the smoking cessation program.

stat.ME↗

arXiv2023

A Matrix Decomposition Model Based on Feature Factors in Movie Recommendation System

Currently, matrix decomposition is one of the most widely used collaborative filtering algorithms by using factor decomposition to effectively deal with large-scale rating matrix. It mainly uses the interaction records between users and items to predict ratings. Based on the characteristic attributes of items and users, this paper proposes a new UISVD++ model that fuses the type attributes of movies and the age attributes of users into SVD++ framework. By projecting the age attribute into the user's implicit space and the type attribute into the item's implicit space, the model enriches the side information of the users and items. At last, we conduct comparative experiments on two public data sets, Movielens-100K and Movielens-1M. Experiment results express that the prediction accuracy of this model is better than other baselines in the task of predicting scores. In addition, these results also show that UISVD++ can effectively alleviate the cold start situation.

cs.IR↗

arXiv2023

EEG-DG: A Multi-Source Domain Generalization Framework for Motor Imagery EEG Classification

Motor imagery EEG classification plays a crucial role in non-invasive Brain-Computer Interface (BCI) research. However, the classification is affected by the non-stationarity and individual variations of EEG signals. Simply pooling EEG data with different statistical distributions to train a classification model can severely degrade the generalization performance. To address this issue, the existing methods primarily focus on domain adaptation, which requires access to the target data during training. This is unrealistic in many EEG application scenarios. In this paper, we propose a novel multi-source domain generalization framework called EEG-DG, which leverages multiple source domains with different statistical distributions to build generalizable models on unseen target EEG data. We optimize both the marginal and conditional distributions to ensure the stability of the joint distribution across source domains and extend it to a multi-source domain generalization framework to achieve domain-invariant feature representation, thereby alleviating calibration efforts. Systematic experiments on a simulative dataset and BCI competition datasets IV-2a and IV-2b demonstrate the superiority of our proposed EEG-DG over state-of-the-art methods. Specifically, EEG-DG achieves an average classification accuracy/kappa value of 81.79%/0.7572 and 87.12%/0.7424 on datasets IV-2a and IV-2b, respectively, which even outperforms some domain adaptation methods. Our code is available at https://github.com/XC-ZhongHIT/EEG-DG for free download and evaluation.

eess.SP↗

arXiv2023

Teacher-Student Architecture for Knowledge Distillation: A Survey

Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their voluminous parameters. To tackle this issue, Teacher-Student architectures were proposed, where simple student networks with a few parameters can achieve comparable performance to deep teacher networks with many parameters. Recently, Teacher-Student architectures have been effectively and widely embraced on various knowledge distillation (KD) objectives, including knowledge compression, knowledge expansion, knowledge adaptation, and knowledge enhancement. With the help of Teacher-Student architectures, current studies are able to achieve multiple distillation objectives through lightweight and generalized student networks. Different from existing KD surveys that primarily focus on knowledge compression, this survey first explores Teacher-Student architectures across multiple distillation objectives. This survey presents an introduction to various knowledge representations and their corresponding optimization objectives. Additionally, we provide a systematic overview of Teacher-Student architectures with representative learning algorithms and effective distillation schemes. This survey also summarizes recent applications of Teacher-Student architectures across multiple purposes, including classification, recognition, generation, ranking, and regression. Lastly, potential research directions in KD are investigated, focusing on architecture design, knowledge quality, and theoretical studies of regression-based learning, respectively. Through this comprehensive survey, industry practitioners and the academic community can gain valuable insights and guidelines for effectively designing, learning, and applying Teacher-Student architectures on various distillation objectives.

cs.LG↗

arXiv2023

Pruning Ternary Quantization

Inference time, model size, and accuracy are three key factors in deep model compression. Most of the existing work addresses these three key factors separately as it is difficult to optimize them all at the same time. For example, low-bit quantization aims at obtaining a faster model; weight sharing quantization aims at improving compression ratio and accuracy; and mixed-precision quantization aims at balancing accuracy and inference time. To simultaneously optimize bit-width, model size, and accuracy, we propose pruning ternary quantization (PTQ): a simple, effective, symmetric ternary quantization method. We integrate L2 normalization, pruning, and the weight decay term to reduce the weight discrepancy in the gradient estimator during quantization, thus producing highly compressed ternary weights. Our method brings the highest test accuracy and the highest compression ratio. For example, it produces a 939kb (49$\times$) 2bit ternary ResNet-18 model with only 4\% accuracy drop on the ImageNet dataset. It compresses 170MB Mask R-CNN to 5MB (34$\times$) with only 2.8\% average precision drop. Our method is verified on image classification, object detection/segmentation tasks with different network structures such as ResNet-18, ResNet-50, and MobileNetV2.

cs.CV↗

arXiv2023

Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure that their hidden and output distributions are consistent, which can be achieved by hierarchical knowledge distillation. However, it is difficult to ensure the distribution consistency simultaneously because the learning of the output distribution depends on the hidden one. In this paper, we propose an adaptive two-stage knowledge distillation method consisting of hidden layer learning and output layer learning. In the former stage, we learn hidden representation with full context by applying mean square error loss function. In the latter stage, we design a power transformation based adaptive smoothness method to learn stable output distribution. It achieved 19\% relative reduction in word error rate, and a faster response for the first token compared with the original streaming model in LibriSpeech corpus.

cs.CL↗

arXiv2023

Ternary Quantization: A Survey

Inference time, model size, and accuracy are critical for deploying deep neural network models. Numerous research efforts have been made to compress neural network models with faster inference and higher accuracy. Pruning and quantization are mainstream methods to this end. During model quantization, converting individual float values of layer weights to low-precision ones can substantially reduce the computational overhead and improve the inference speed. Many quantization methods have been studied, for example, vector quantization, low-bit quantization, and binary/ternary quantization. This survey focuses on ternary quantization. We review the evolution of ternary quantization and investigate the relationships among existing ternary quantization methods from the perspective of projection function and optimization methods.

cs.LG↗

arXiv2023

Flexible Alignment Super-Resolution Network for Multi-Contrast MRI

Magnetic resonance imaging plays an essential role in clinical diagnosis by acquiring the structural information of biological tissue. Recently, many multi-contrast MRI super-resolution networks achieve good effects. However, most studies ignore the impact of the inappropriate foreground scale and patch size of multi-contrast MRI, which probably leads to inappropriate feature alignment. To tackle this problem, we propose the Flexible Alignment Super-Resolution Network (FASR-Net) for multi-contrast MRI Super-Resolution. The Flexible Alignment module of FASR-Net consists of two modules for feature alignment. (1) The Single-Multi Pyramid Alignment(S-A) module solves the situation where low-resolution (LR) images and reference (Ref) images have different scales. (2) The Multi-Multi Pyramid Alignment(M-A) module solves the situation where LR and Ref images have the same scale. Besides, we propose the Cross-Hierarchical Progressive Fusion (CHPF) module aiming at fusing the features effectively, further improving the image quality. Compared with other state-of-the-art methods, FASR-net achieves the most competitive results on FastMRI and IXI datasets. Our code will be available at \href{https://github.com/yimingliu123/FASR-Net}{https://github.com/yimingliu123/FASR-Net}.

eess.IV↗

arXiv2022

Hyperspherical Loss-Aware Ternary Quantization

Most of the existing works use projection functions for ternary quantization in discrete space. Scaling factors and thresholds are used in some cases to improve the model accuracy. However, the gradients used for optimization are inaccurate and result in a notable accuracy gap between the full precision and ternary models. To get more accurate gradients, some works gradually increase the discrete portion of the full precision weights in the forward propagation pass, e.g., using temperature-based Sigmoid function. Instead of directly performing ternary quantization in discrete space, we push full precision weights close to ternary ones through regularization term prior to ternary quantization. In addition, inspired by the temperature-based method, we introduce a re-scaling factor to obtain more accurate gradients by simulating the derivatives of Sigmoid function. The experimental results show that our method can significantly improve the accuracy of ternary quantization in both image classification and object detection tasks.

cs.CV↗