papers

Publications (265)

math.NT2020

Dyadic Approximation in the Middle-Third Cantor Set

Demi Allen, Sam Chow, Han Yu

In this paper, we study the metric theory of dyadic approximation in the middle-third Cantor set. This theory complements earlier work of Levesley, Salp, and Velani (2007), who inv…

cs.LG2025

LEAVES: Learning Views for Time-Series Biobehavioral Data in Contrastive Learning

Han Yu, Huiyuan Yang, Akane Sano

Contrastive learning has been utilized as a promising self-supervised learning approach to extract meaningful representations from unlabeled data. The majority of these methods tak…

cs.LG2025

DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning

Shuaipeng Zhang, Lanju Kong, Yixin Zhang +4

Due to the distributed nature of federated learning (FL), the vulnerability of the global model and the need for coordination among many client devices pose significant challenges.…

eess.SP2023

Aggregating Intrinsic Information to Enhance BCI Performance through Federated Learning

Rui Liu, Yuanyuan Chen, Anran Li +3

Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes co…

quant-ph2023

Elastic Entangled Pair and Qubit Resource Management in Quantum Cloud Computing

Rakpong Kaewpuang, Minrui Xu, Dinh Thai Hoang +5

Quantum cloud computing (QCC) offers a promising approach to efficiently provide quantum computing resources, such as quantum computers, to perform resource-intensive tasks. Like t…

cs.CV2024

GAQAT: gradient-adaptive quantization-aware training for domain generalization

Jiacheng Jiang, Yuan Meng, Chen Tang +4

Research on loss surface geometry, such as Sharpness-Aware Minimization (SAM), shows that flatter minima improve generalization. Recent studies further reveal that flatter minima c…

cs.CR2019

Reviewing and Improving the Gaussian Mechanism for Differential Privacy

Jun Zhao, Teng Wang, Tao Bai +7

Differential privacy provides a rigorous framework to quantify data privacy, and has received considerable interest recently. A randomized mechanism satisfying -different…

cs.SE2014

Identifying Talented Software Engineering Students through Data-driven Skill Assessment

Jun Lin, Han Yu, Zhiqi Shen

For software development companies, one of the most important objectives is to identify and acquire talented software engineers in order to maintain a skilled team that can produce…

cs.LG2026

From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity

Zhuang Qi, Ying-Peng Tang, Lei Meng +4

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. E…

cs.CL2026

A cross-species neural foundation model for end-to-end speech decoding

Yizi Zhang, Linyang He, Chaofei Fan +9

Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that d…

cs.LG2025

Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections

Wei Zhuo, Zhaohuan Zhan, Han Yu

Federated Learning (FL) on graph-structured data typically faces non-IID challenges, particularly in scenarios where each client holds a distinct subgraph sampled from a global gra…

math.MG2021

On the Hausdorff dimension of microsets

Jonathan M. Fraser, Douglas C. Howroyd, Antti Käenmäki +1

We investigate how the Hausdorff dimensions of microsets are related to the dimensions of the original set. It is known that the maximal dimension of a microset is the Assouad dime…

cs.LG2023

FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learning

Anran Li, Hongyi Peng, Lan Zhang +4

Vertical Federated Learning (VFL) enables multiple data owners, each holding a different subset of features about largely overlapping sets of data sample(s), to jointly train a use…

physics.ins-det2018

A multi-channel DAQ system based on FPGA for long-distance transmission in nuclear physics experiments

Hongwei Yu, Kezhu Song, Junfeng Yang +5

As the development of electronic science and technology, electronic data acquisition (DAQ) system is more and more widely applied to nuclear physics experiments. Workstations are o…

cs.AI2025

Federated Cross-Training Learners for Robust Generalization under Data Heterogeneity

Zhuang Qi, Lei Meng, Ruohan Zhang +5

Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve generalization capability. However, due to inhere…

cs.LG2022

Empirical Evaluation of Data Augmentations for Biobehavioral Time Series Data with Deep Learning

Huiyuan Yang, Han Yu, Akane Sano

Deep learning has performed remarkably well on many tasks recently. However, the superior performance of deep models relies heavily on the availability of a large number of trainin…

cs.CR2022

Towards Verifiable Federated Learning

Yanci Zhang, Han Yu

Federated learning (FL) is an emerging paradigm of collaborative machine learning that preserves user privacy while building powerful models. Nevertheless, due to the nature of ope…

cs.SE2014

An Empirical Analysis of Task Allocation in Scrum-based Agile Programming

Jun Lin, Han Yu, Zhiqi Shen

Agile Software Development (ASD) methodology has become widely used in the industry. Understanding the challenges facing software engineering students is important to designing eff…

math.NT2021

Rational points near self-similar sets

Han Yu

In this paper, we consider a problem of counting rational points near self-similar sets. Let be an integer. We shall show that for some self-similar measures on $\mathbb{…

math.NT2021

An improvement on Furstenberg's intersection problem

Han Yu

In this paper, we study a problem posed by Furstenberg on intersections between invariant sets. We present here a direct geometrical counting argument to revis…

cs.CV2018

Cross-position Activity Recognition with Stratified Transfer Learning

Yiqiang Chen, Jindong Wang, Meiyu Huang +1

Human activity recognition aims to recognize the activities of daily living by utilizing the sensors on different body parts. However, when the labeled data from a certain body pos…

cs.LG2025

Can Textual Gradient Work in Federated Learning?

Minghui Chen, Ruinan Jin, Wenlong Deng +4

Recent studies highlight the promise of LLM-based prompt optimization, especially with TextGrad, which automates differentiation'' via texts and backpropagates textual feedback. Th…

cs.CL2022

On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey

Xu Guo, Han Yu

Recent advances in NLP are brought by a range of large-scale pretrained language models (PLMs). These PLMs have brought significant performance gains for a range of NLP tasks, circ…

cs.LG2022

PiRL: Participant-Invariant Representation Learning for Healthcare

Zhaoyang Cao, Han Yu, Huiyuan Yang +1

Due to individual heterogeneity, performance gaps are observed between generic (one-size-fits-all) models and person-specific models in data-driven health applications. However, in…

cs.IT2023

Learning to Code on Graphs for Topological Interference Management

Zhiwei Shan, Xinping Yi, Han Yu +2

The state-of-the-art coding schemes for topological interference management (TIM) problems are usually handcrafted for specific families of network topologies, relying critically o…

cs.LG2020

FOCUS: Dealing with Label Quality Disparity in Federated Learning

Yiqiang Chen, Xiaodong Yang, Xin Qin +3

Ubiquitous systems with End-Edge-Cloud architecture are increasingly being used in healthcare applications. Federated Learning (FL) is highly useful for such applications, due to s…

math.PR2018

Assouad dimension of random processes

Douglas Howroyd, Han Yu

In this paper we study the Assouad dimension of graphs of certain Lévy processes and functions defined by stochastic integrals. We do this by introducing a convenient condition wh…

cs.HC2023

Towards the Understanding of Receptivity and Affect in EMAs using Physiological based Machine Learning Method: Analysis of Receptivity and Affect

Zachary D King, Han Yu, Thomas Vaessen +2

As mobile health (mHealth) studies become increasingly productive due to the advancements in wearable and mobile sensor technology, our ability to monitor and model human behavior…

cs.CV2021

Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

Chang Liu, Han Yu, Boyang Li +6

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness…

math.NT2025

Moment transference principles and multiplicative diophantine approximation on hypersurfaces

Sam Chow, Han Yu

We determine the generic multiplicative approximation rate on a hypersurface. There are four regimes, according to convergence or divergence and curved or flat, and we address all…

cs.CL2026

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

DeepSeek-AI, Anyi Xu, Bangcai Lin +315

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…

math.NT2021

On the metric theory of inhomogeneous Diophantine approximation: An Erdős-Vaaler type result

Han Yu

In 1958, Szüsz proved an inhomogeneous version of Khintchine's theorem on Diophantine approximation. Szüsz's theorem states that for any non-increasing approximation function $ψ…

cs.IR2026

From Transfer to Collaboration: A Federated Framework for Cross-Market Sequential Recommendation

Jundong Chen, Honglei Zhang, Xiangmou Qu +3

Cross-market recommendation (CMR) aims to enhance recommendation performance across multiple markets. Due to its inherent characteristics, i.e., data isolation, non-overlapping use…

cs.CY2023

Towards AI-Empowered Crowdsourcing

Shipeng Wang, Qingzhong Li, Lizhen Cui +6

Crowdsourcing, in which human intelligence and productivity is dynamically mobilized to tackle tasks too complex for automation alone to handle, has grown to be an important resear…

math.NT2018

A Fourier analytic approach to inhomogeneous Diophantine approximation

Han Yu

In this paper, we study inhomogeneous Diophantine approximation with rational numbers of reduced form. The central object to study is the set as follows, \begin{eqnarray*…

cs.LG2024

A Note on LoRA

Vlad Fomenko, Han Yu, Jongho Lee +2

LoRA (Low-Rank Adaptation) has emerged as a preferred method for efficiently adapting Large Language Models (LLMs) with remarkable simplicity and efficacy. This note extends the or…

cs.LG2025

Uncertainty-Aware Explainable Federated Learning

Yanci Zhang, Han Yu

Federated Learning (FL) is a collaborative machine learning paradigm for enhancing data privacy preservation. Its privacy-preserving nature complicates the explanation of the decis…

cs.CL2024

Learning from "Silly" Questions Improves Large Language Models, But Only Slightly

Tingyuan Zhu, Shudong Liu, Yidong Wang +4

Constructing high-quality Supervised Fine-Tuning (SFT) datasets is critical for the training of large language models (LLMs). Recent studies have shown that using data from a speci…

math.NT2022

A note on dyadic approximation in Cantor's set

Demi Allen, Simon Baker, Sam Chow +1

We consider the convergence theory for dyadic approximation in the middle-third Cantor set, , for approximation functions of the form (). In partic…

cs.AI2016

A Survey on Artificial Intelligence and Data Mining for MOOCs

Simon Fauvel, Han Yu

Massive Open Online Courses (MOOCs) have gained tremendous popularity in the last few years. Thanks to MOOCs, millions of learners from all over the world have taken thousands of h…

cs.CV2018

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

Jindong Wang, Wenjie Feng, Yiqiang Chen +3

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-dom…

cs.IT2026

Information-Theoretic Decentralized Secure Aggregation with User Dropouts

Zhou Li, Xiang Zhang, Yizhou Zhao +2

This paper investigates the fundamental limits of information-theoretic decentralized secure aggregation (DSA) with user dropouts. We consider a fully decentralized network where $…

cs.LG2019

Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Jiawen Kang, Zehui Xiong, Dusit Niyato +3

To strengthen data privacy and security, federated learning as an emerging machine learning technique is proposed to enable large-scale nodes, e.g., mobile devices, to distributedl…

cs.CR2022

Adaptive Resource Allocation in Quantum Key Distribution (QKD) for Federated Learning

Rakpong Kaewpuang, Minrui Xu, Dusit Niyato +3

Increasing privacy and security concerns in intelligence-native 6G networks require quantum key distribution-secured federated learning (QKD-FL), in which data owners connected via…

math.DS2022

Bernoulli convolutions with Garsia parameters in have continuous density functions

Han Yu

Let be an algebraic integer with Mahler measure A classical result of Garsia shows that the Bernoulli convolution is absolutely continuous with re…

math.DS2022

Times two, three, five orbits on

Han Yu

In this paper, we study orbit closures under diagonal torus actions. We show that if is not contained in any rational lines, then its orbit under the $\times…

cs.CL2024

Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs

Yifei Zhang, Hao Zhu, Aiwei Liu +3

Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant ch…

cs.LG2025

Ten Challenging Problems in Federated Foundation Models

Tao Fan, Hanlin Gu, Xuemei Cao +30

Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of fed…

math.NT2026

Counting rationals and diophantine approximation in missing-digit Cantor sets

Sam Chow, Péter P. Varjú, Han Yu

We establish a new upper bound for the number of rationals up to a given height in a missing-digit set, making progress towards a conjecture of Broderick, Fishman, and Reich. This…

cs.CL2025

Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models

Chuan Sun, Han Yu, Lizhen Cui +1

Pruning large language models (LLMs) is a promising solution for reducing model sizes and computational complexity while preserving performance. Traditional layer-wise pruning meth…

cs.IT2026

Topology-Aware Coordination for Multi-Functional Low-Altitude Wireless Networks

Jiajun He, Han Yu, Yiran Guo +6

Low-altitude wireless networks (LAWNs) are expected to consist of multi-tier, heterogeneous terrestrial and non-terrestrial devices, where effective coordination is essential to fu…

math.NT2022

Fractal projections with an application in number theory

Han Yu

In this paper, we discuss a connection between geometric measure theory and number theory. This method brings a new point of view for some number-theoretic problems concerning digi…

stat.ML2024

Double Machine Learning for Adaptive Causal Representation in High-Dimensional Data

Lynda Aouar, Han Yu

Adaptive causal representation learning from observational data is presented, integrated with an efficient sample splitting technique within the semiparametric estimating equation…

cs.IT2026

Topology-Aware Integrated Communication, Sensing, and Power Transfer for SAGIN

Han Yu, Jiajun He, Xinping Yi +3

The space-air-ground integrated network (SAGIN) has garnered significant attention in recent years due to its capability to extend communication networks from terrestrial environme…

cs.LG2025

FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learning

Yuanyuan Chen, Zichen Chen, Pengcheng Wu +1

Large-scale neural networks possess considerable expressive power. They are well-suited for complex learning tasks in industrial applications. However, large-scale models pose sign…

cs.LG2023

Hierarchical Federated Learning Incentivization for Gas Usage Estimation

Has Sun, Xiaoli Tang, Chengyi Yang +5

Accurately estimating gas usage is essential for the efficient functioning of gas distribution networks and saving operational costs. Traditional methods rely on centralized data p…

cs.MA2014

An Evolutionary Approach for Optimizing Hierarchical Multi-Agent System Organization

Zhiqi Shen, Ling Yu, Han Yu

It has been widely recognized that the performance of a multi-agent system is highly affected by its organization. A large scale system may have billions of possible ways of organi…

cs.LG2025

SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning

Yuning Yang, Han Yu, Chuan Sun +5

Federated Learning (FL) is a collaborative machine learning paradigm for training models on local sensitive data with privacy protection. Pre-trained transformer-based models have…

cs.AI2023

LR-XFL: Logical Reasoning-based Explainable Federated Learning

Yanci Zhang, Han Yu

Federated learning (FL) is an emerging approach for training machine learning models collaboratively while preserving data privacy. The need for privacy protection makes it difficu…

cs.LG2026

A Survey on Federated Causal Discovery and Inference

Xianjie Guo, Yuwei Wang, Guodu Xiang +4

Causal reasoning, which encompasses the discovery of causal structures and the inference of causal effects, is fundamental to data-driven decision making. In practice, data for rel…

eess.SY2024

Fairness-Aware Multi-Server Federated Learning Task Delegation over Wireless Networks

Yulan Gao, Chao Ren, Han Yu

In the rapidly advancing field of federated learning (FL), ensuring efficient FL task delegation while incentivising FL client participation poses significant challenges, especiall…

cs.LG2020

Multi-Participant Multi-Class Vertical Federated Learning

Siwei Feng, Han Yu

Federated learning (FL) is a privacy-preserving paradigm for training collective machine learning models with locally stored data from multiple participants. Vertical federated lea…

cs.LG2025

Error Slice Discovery via Manifold Compactness

Han Yu, Hao Zou, Jiashuo Liu +4

Despite the great performance of deep learning models in many areas, they still make mistakes and underperform on certain subsets of data, i.e. error slices. Given a trained model,…

cs.CR2020

Federated Crowdsensing: Framework and Challenges

Leye Wang, Han Yu, Xiao Han

Crowdsensing is a promising sensing paradigm for smart city applications (e.g., traffic and environment monitoring) with the prevalence of smart mobile devices and advanced network…

math.CA2017

On generalized trigonometric functions and series of rational functions

Han Yu

Here we introduce a way to construct generalized trigonometric functions associated with any complex polynomials, and the well known trigonometric functions can be seen to associat…

cs.MM2019

Generating Persuasive Visual Storylines for Promotional Videos

Chang Liu, Yi Dong, Han Yu +8

Video contents have become a critical tool for promoting products in E-commerce. However, the lack of automatic promotional video generation solutions makes large-scale video-based…

cs.LG2025

Commute Graph Neural Networks

Wei Zhuo, Han Yu, Guang Tan +1

Graph Neural Networks (GNNs) have shown remarkable success in learning from graph-structured data. However, their application to directed graphs (digraphs) presents unique challeng…

cs.LG2023

Recurrent Temporal Revision Graph Networks

Yizhou Chen, Anxiang Zeng, Guangda Huzhang +6

Temporal graphs offer more accurate modeling of many real-world scenarios than static graphs. However, neighbor aggregation, a critical building block of graph networks, for tempor…

cs.CR2022

Resource Allocation in Quantum Key Distribution (QKD) for Space-Air-Ground Integrated Networks

Rakpong Kaewpuang, Minrui Xu, Dusit Niyato +2

Space-air-ground integrated networks (SAGIN) are one of the most promising advanced paradigms in the sixth generation (6G) communication. SAGIN can support high data rates, low lat…

cs.CL2021

Automatic Product Copywriting for E-Commerce

Xueying Zhang, Yanyan Zou, Hainan Zhang +10

Product copywriting is a critical component of e-commerce recommendation platforms. It aims to attract users' interest and improve user experience by highlighting product character…

cs.LG2024

Towards Quantum Federated Learning

Chao Ren, Rudai Yan, Huihui Zhu +9

Quantum Federated Learning (QFL) is an emerging interdisciplinary field that merges the principles of Quantum Computing (QC) and Federated Learning (FL), with the goal of leveragin…

cs.CR2021

Securing Federated Learning: A Covert Communication-based Approach

Yuan-Ai Xie, Jiawen Kang, Dusit Niyato +4

Federated Learning Networks (FLNs) have been envisaged as a promising paradigm to collaboratively train models among mobile devices without exposing their local privacy data. Due t…

cs.LG2023

The Prospect of Enhancing Large-Scale Heterogeneous Federated Learning with Transformers

Yulan Gao, Zhaoxiang Hou, Chengyi Yang +2

Federated learning (FL) addresses data privacy concerns by enabling collaborative training of AI models across distributed data owners. Wide adoption of FL faces the fundamental ch…

math.NT2025

Numbers omitting digits in certain base expansions

Alexia Yavicoli, Han Yu

In DOI:10.1017/etds.2022.2 the author proved that for each integer there is an implicit number such that if are multiplicatively independent integer…

math.OC2022

Robust Optimization with Decision-Dependent Information Discovery

Phebe Vayanos, Angelos Georghiou, Han Yu

Robust optimization is a popular paradigm for modeling and solving two- and multi-stage decision-making problems affected by uncertainty. In many real-world applications, the time…

cs.AI2023

Clustered Embedding Learning for Recommender Systems

Yizhou Chen, Guangda Huzhang, Anxiang Zeng +7

In recent years, recommender systems have advanced rapidly, where embedding learning for users and items plays a critical role. A standard method learns a unique embedding vector f…

cs.CR2022

Privacy and Robustness in Federated Learning: Attacks and Defenses

Lingjuan Lyu, Han Yu, Xingjun Ma +5

As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (…

cs.CV2016

Surveillance Video Parsing with Single Frame Supervision

Si Liu, Changhu Wang, Ruihe Qian +2

Surveillance video parsing, which segments the video frames into several labels, e.g., face, pants, left-leg, has wide applications. However,pixel-wisely annotating all frames is t…

cs.AI2018

Building Ethics into Artificial Intelligence

Han Yu, Zhiqi Shen, Chunyan Miao +3

As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination. Within the AI…

eess.SY2022

Multi-Resource Allocation for On-Device Distributed Federated Learning Systems

Yulan Gao, Ziqiang Ye, Han Yu +3

This work poses a distributed multi-resource allocation scheme for minimizing the weighted sum of latency and energy consumption in the on-device distributed federated learning (FL…

cs.LG2022

Bias Reducing Multitask Learning on Mental Health Prediction

Khadija Zanna, Kusha Sridhar, Han Yu +1

There has been an increase in research in developing machine learning models for mental health detection or prediction in recent years due to increased mental health issues in soci…

eess.SP2024

ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Text

Han Yu, Peikun Guo, Akane Sano

The utilization of deep learning on electrocardiogram (ECG) analysis has brought the advanced accuracy and efficiency of cardiac healthcare diagnostics. By leveraging the capabilit…

math.CA2017

Arithmetic patches, weak tangents, and dimension

Jonathan M. Fraser, Han Yu

We investigate the relationships between several classical notions in arithmetic combinatorics and geometry including: the presence (or lack of) arithmetic progressions (or patches…

cond-mat.mtrl-sci2026

Wafer-scale hybrid molecular beam epitaxy of BaTiO3 and SrTiO3 on silicon

Xiaodong Tian, Yan Lin, Hanbin Gao +8

The integration of epitaxial barium titanate (BTO) on silicon represents a highly promising pathway for next-generation, energy-efficient photonic integrated circuits due to BTO's…

cs.LG2021

Advances and Open Problems in Federated Learning

Peter Kairouz, H. Brendan McMahan, Brendan Avent +56

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a cen…

cs.LG2024

Federated Model Heterogeneous Matryoshka Representation Learning

Liping Yi, Han Yu, Chao Ren +3

Model heterogeneous federated learning (MHeteroFL) enables FL clients to collaboratively train models with heterogeneous structures in a distributed fashion. However, existing MHet…

math.CA2017

Kakeya books and projections of Kakeya sets

Han Yu

Here we show some results related with Kakeya conjecture which says that for any integer , a set containing line segments in every dimension in has full Hau…

cs.CV2025

Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning

Zhuang Qi, Pan Yu, Lei Meng +4

Federated Prompt Learning (FPL) enables communication-efficient adaptation by tuning lightweight prompts on top of frozen pre-trained models. Existing FPL methods typically rely on…

cs.LG2025

HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks

Yuanyuan Chen, Boyang Li, Han Yu +2

The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HYDRA, which in…

cs.LG2025

Class-wise Balancing Data Replay for Federated Class-Incremental Learning

Zhuang Qi, Ying-Peng Tang, Lei Meng +3

Federated Class Incremental Learning (FCIL) aims to collaboratively process continuously increasing incoming tasks across multiple clients. Among various approaches, data replay ha…

physics.geo-ph2024

A Joint Inversion of Sources and Seismic Waveforms for Velocity Distribution: 1-D and 2-D Examples

Han Yu

Waveform inversion is theoretically a powerful tool to reconstruct subsurface structures, but a usually encountered problem is that accurate sources are very rare, causing the comp…

math.MG2021

Dimensions of the popcorn graph

Haipeng Chen, Jonathan M. Fraser, Han Yu

The 'popcorn function' isThe `popcorn function' is a well-known and important example in real analysis with many interesting features. We prove that the box dimension of the graph…

eess.SP2022

Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild

Han Yu, Akane Sano

Physiological and behavioral data collected from wearable or mobile sensors have been used to estimate self-reported stress levels. Since the stress annotation usually relies on se…

math.DS2021

Additive properties of numbers with restricted digits

Han Yu

In this paper, we consider some additive properties of integers with restricted digit expansions. Let be an integer and be the set of integers whose base expans…

cs.CV2023

Image Aesthetics Assessment via Learnable Queries

Zhiwei Xiong, Yunfan Zhang, Zhiqi Shen +2

Image aesthetics assessment (IAA) aims to estimate the aesthetics of images. Depending on the content of an image, diverse criteria need to be selected to assess its aesthetics. Ex…

cs.LG2025

Local Data Quantity-Aware Weighted Averaging for Federated Learning with Dishonest Clients

Leming Wu, Yaochu Jin, Kuangrong Hao +1

Federated learning (FL) enables collaborative training of deep learning models without requiring data to leave local clients, thereby preserving client privacy. The aggregation pro…

cs.MA2016

Building Robust Crowdsourcing Systems with Reputation-aware Decision Support Techniques

Han Yu

Crowdsourcing refers to the arrangement in which contributions are solicited from a large group of unrelated people. Due to this nature, crowdsourcers (or task requesters) often fa…

cs.LG2026

TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning

Suizhi Huang, Mei Li, Han Yu +1

Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause o…

math.NT2022

On the metric theory of multiplicative Diophantine approximation

Han Yu

In 1962, Gallagher proved an higher dimensional version of Khintchine's theorem on Diophantine approximation. Gallagher's theorem states that for any non-increasing approximation f…

cs.CL2022

Federated Learning for Personalized Humor Recognition

Xu Guo, Han Yu, Boyang Li +5

Computational understanding of humor is an important topic under creative language understanding and modeling. It can play a key role in complex human-AI interactions. The challeng…