arXiv subjects

Hanwen Liu

Publications and source records attributed to Hanwen Liu.

At least 37 records · Page 2Linked to original sources

arXiv2025

MSGM: A Multi-Scale Spatiotemporal Graph Mamba for EEG Emotion Recognition

EEG-based emotion recognition struggles with capturing multi-scale spatiotemporal dynamics and ensuring computational efficiency for real-time applications. Existing methods often oversimplify temporal granularity and spatial hierarchies, limiting accuracy. To overcome these challenges, we propose the Multi-Scale Spatiotemporal Graph Mamba (MSGM), a novel framework integrating multi-window temporal segmentation, bimodal spatial graph modeling, and efficient fusion via the Mamba architecture. By segmenting EEG signals across diverse temporal scales and constructing global-local graphs with neuroanatomical priors, MSGM effectively captures fine-grained emotional fluctuations and hierarchical brain connectivity. A multi-depth Graph Convolutional Network (GCN) and token embedding fusion module, paired with Mamba's state-space modeling, enable dynamic spatiotemporal interaction at linear complexity. Notably, with just one MSST-Mamba layer, MSGM surpasses leading methods in the field on the SEED, THU-EP, and FACED datasets, outperforming baselines in subject-independent emotion classification while achieving robust accuracy and millisecond-level inference on the NVIDIA Jetson Xavier NX.

eess.SP↗

arXiv2025

HyDRA: A Hybrid Dual-Mode Network for Closed- and Open-Set RFFI with Optimized VMD

Device recognition is vital for security in wireless communication systems, particularly for applications like access control. Radio Frequency Fingerprint Identification (RFFI) offers a non-cryptographic solution by exploiting hardware-induced signal distortions. This paper proposes HyDRA, a Hybrid Dual-mode RF Architecture that integrates an optimized Variational Mode Decomposition (VMD) with a novel architecture based on the fusion of Convolutional Neural Networks (CNNs), Transformers, and Mamba components, designed to support both closed-set and open-set classification tasks. The optimized VMD enhances preprocessing efficiency and classification accuracy by fixing center frequencies and using closed-form solutions. HyDRA employs the Transformer Dynamic Sequence Encoder (TDSE) for global dependency modeling and the Mamba Linear Flow Encoder (MLFE) for linear-complexity processing, adapting to varying conditions. Evaluation on public datasets demonstrates state-of-the-art (SOTA) accuracy in closed-set scenarios and robust performance in our proposed open-set classification method, effectively identifying unauthorized devices. Deployed on NVIDIA Jetson Xavier NX, HyDRA achieves millisecond-level inference speed with low power consumption, providing a practical solution for real-time wireless authentication in real-world environments.

cs.LG↗

arXiv2025

Conformal Prediction for Verifiable Learned Query Optimization

Query optimization is critical in relational databases. Recently, numerous Learned Query Optimizers (LQOs) have been proposed, demonstrating superior performance over traditional hand-crafted query optimizers after short training periods. However, the opacity and instability of machine learning models have limited their practical applications. To address this issue, we are the first to formulate the LQO verification as a Conformal Prediction (CP) problem. We first construct the CP model and obtain user-controlled bounded ranges for the actual latency of LQO plans before execution. Then, we introduce CP-based runtime verification along with violation handling to ensure performance prior to execution. For both scenarios, we further extend our framework to handle distribution shifts in the dynamic environment using adaptive CP approaches. Finally, we present CP-guided plan search, which uses actual latency upper bounds from CP to heuristically guide query plan construction. We integrated our verification framework into three LQOs (Balsa, Lero, and RTOS) and conducted evaluations on the JOB and TPC-H workloads. Experimental results demonstrate that our method is both accurate and efficient. Our CP-based approaches achieve tight upper bounds, reliably detect and handle violations. Adaptive CP maintains accurate confidence levels even in the presence of distribution shifts, and the CP-guided plan search improves both query plan quality (up to 9.84x) and planning time, with a reduction of up to 74.4% for a single query and 9.96% across all test queries from trained LQOs.

cs.DB↗

arXiv2024

PMSN: A Parallel Multi-compartment Spiking Neuron for Multi-scale Temporal Processing

Spiking Neural Networks (SNNs) hold great potential to realize brain-inspired, energy-efficient computational systems. However, current SNNs still fall short in terms of multiscale temporal processing compared to their biological counterparts. This limitation has resulted in poor performance in many pattern recognition tasks with information that varies across different timescales. To address this issue, we put forward a novel spiking neuron model called Parallel Multi-compartment Spiking Neuron (PMSN). The PMSN emulates biological neurons by incorporating multiple interacting substructures and allows for flexible adjustment of the substructure counts to effectively represent temporal information across diverse timescales. Additionally, to address the computational burden associated with the increased complexity of the proposed model, we introduce two parallelization techniques that decouple the temporal dependencies of neuronal updates, enabling parallelized training across different time steps. Our experiments across a wide range of pattern recognition tasks demonstrate that PMSN outperforms state-of-the-art spiking neuron models in temporal processing capacity and training speed. Specifically, compared with the commonly used Leaky Integrate-and-Fire neuron, PMSN offers more than 10 times acceleration and a 30% accuracy improvement on Sequential CIFAR-10 dataset, while maintaining comparable computational cost. Our implementation on neuromorphic hardware further demonstrates the deployability of PMSN and highlights its favorable trade-off between effectiveness and efficiency. Therefore, the proposed PMSN presents a promising solution to harness the computational advantages of detailed biological neurons, enabling high-performance and efficient temporal processing on neuromorphic computing systems. Code is available at https://github.com/xychen-comp/PMSN.

cs.NE↗

arXiv2024

Accelerating Low-Rank Factorization-Based Semidefinite Programming Algorithms on GPU

In this paper, we address a long-standing challenge: how to achieve both efficiency and scalability in solving semidefinite programming problems. We propose breakthrough acceleration techniques for a wide range of low-rank factorization-based first-order methods using GPUs, making the computation much more efficient and scalable. To illustrate the idea and effectiveness of our approach, we use the low-rank factorization-based SDP solver, LoRADS, as an example, which involves both the classic Burer-Monterio method and a novel splitting scheme with a starting logarithmic rank. Our numerical results demonstrate that the accelerated GPU version of LoRADS, cuLoRADS, can solve huge-scale semidefinite programming problems with remarkable efficiency. By effectively leveraging GPU computational power, cuLoRADS exhibits outstanding performance. Specifically, it can solve a set of MaxCut problems with $10^7 \times 10^7$ matrix variables in 10 seconds to 1 minute each on an NVIDIA H100 GPU with 80GB memory, whereas previous solvers demonstrated the capability of handling problems of this scale, required at least dozens of hours per problem on CPUs. Additionally, cuLoRADS shows exceptional scalability by solving 1) a MaxCut problem with a $170 \text{ million} \times 170 \text{ million}$ matrix variable and 2) a Matrix Completion problem with a 20 million $\times$ 20 million matrix variable and approximately 200 million constraints, both in a matter of minutes.

math.OC↗

arXiv2024

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication. To address this, we propose a soft deduplication method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness. Central to our approach is the concept of "data commonness", a metric we introduce to quantify the degree of duplication by measuring the occurrence probabilities of samples using an n-gram model. Empirical analysis shows that this method significantly improves training efficiency, achieving comparable perplexity scores with at least a 26% reduction in required training steps. Additionally, it enhances average few-shot downstream accuracy by 1.77% when trained for an equivalent duration. Importantly, this approach consistently improves performance, even on rigorously deduplicated datasets, indicating its potential to complement existing methods and become a standard pre-training process for LLMs.

cs.CL↗

arXiv2024

Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation

Integrating information from various reference databases is a major challenge for Retrieval-Augmented Generation (RAG) systems because each knowledge source adopts a unique data structure and follows different conventions. Retrieving from multiple knowledge sources with one fixed strategy usually leads to under-exploitation of information. To mitigate this drawback, inspired by Mix-of-Expert, we introduce Mix-of-Granularity (MoG), a method that dynamically determines the optimal granularity of a knowledge source based on input queries using a router. The router is efficiently trained with a newly proposed loss function employing soft labels. We further extend MoG to MoG-Graph (MoGG), where reference documents are pre-processed as graphs, enabling the retrieval of distantly situated snippets. Experiments demonstrate that MoG and MoGG effectively predict optimal granularity levels, significantly enhancing the performance of the RAG system in downstream tasks. The code of both MoG and MoGG are released in https://github.com/ZGChung/Mix-of-Granularity.

cs.LG↗

arXiv2024

EEG2TEXT: Open Vocabulary EEG-to-Text Decoding with EEG Pre-Training and Multi-View Transformer

Deciphering the intricacies of the human brain has captivated curiosity for centuries. Recent strides in Brain-Computer Interface (BCI) technology, particularly using motor imagery, have restored motor functions such as reaching, grasping, and walking in paralyzed individuals. However, unraveling natural language from brain signals remains a formidable challenge. Electroencephalography (EEG) is a non-invasive technique used to record electrical activity in the brain by placing electrodes on the scalp. Previous studies of EEG-to-text decoding have achieved high accuracy on small closed vocabularies, but still fall short of high accuracy when dealing with large open vocabularies. We propose a novel method, EEG2TEXT, to improve the accuracy of open vocabulary EEG-to-text decoding. Specifically, EEG2TEXT leverages EEG pre-training to enhance the learning of semantics from EEG signals and proposes a multi-view transformer to model the EEG signal processing by different spatial regions of the brain. Experiments show that EEG2TEXT has superior performance, outperforming the state-of-the-art baseline methods by a large margin of up to 5% in absolute BLEU and ROUGE scores. EEG2TEXT shows great potential for a high-performance open-vocabulary brain-to-text system to facilitate communication.

cs.CL↗

arXiv2024

Some Computational Results on Koszul-Vinberg Cochain Complexes

An affine connection is said to be flat if its curvature tensor vanishes identically. Koszul-Vinberg (KV for abbreviation) cohomology has been invoked to study the deformation theory of flat and torsion-free affine connections on tangent bundle. In this Note, we compute explicitly the differentials of various specific KV cochains, and study their relation to classical objects in information geometry, including deformations associated with projective and dual-projective transformations of a flat and torsion-free affine connection. As an application, we also give a simple yet non-trivial example of a KV algebra of which second cohomology group does not vanish.

math.DG↗

arXiv2024

Corra: Correlation-Aware Column Compression

Column encoding schemes have witnessed a spark of interest with the rise of open storage formats (like Parquet) in data lakes in modern cloud deployments. This is not surprising -- as data volume increases, it becomes more and more important to reduce storage cost on block storage (such as S3) as well as reduce memory pressure in multi-tenant in-memory buffers of cloud databases. However, single-column encoding schemes have reached a plateau in terms of the compression size they can achieve. We argue that this is due to the neglect of cross-column correlations. For instance, consider the column pair ($\texttt{city}$, $\texttt{zip_code}$). Typically, cities have only a few dozen unique zip codes. If this information is properly exploited, it can significantly reduce the space consumption of the latter column. In this work, we depart from the established path of compressing data using only single-column encoding schemes and introduce several what we call $\textit{horizontal}$, correlation-aware encoding schemes. We demonstrate their advantages over single-column encoding schemes on the well-known TPC-H's $\texttt{lineitem}$, LDBC's $\texttt{message}$, DMV, and Taxi datasets. Our correlation-aware encoding schemes save up to 58.3% of the compressed size over single-column schemes for $\texttt{lineitem}$'s $\texttt{receiptdate}$, 53.7% for DMV's $\texttt{zip_code}$, and 85.16% for Taxi's $\texttt{total_amount}$.

cs.DB↗

arXiv2024

AI for Biomedicine in the Era of Large Language Models

The capabilities of AI for biomedicine span a wide spectrum, from the atomic level, where it solves partial differential equations for quantum systems, to the molecular level, predicting chemical or protein structures, and further extending to societal predictions like infectious disease outbreaks. Recent advancements in large language models, exemplified by models like ChatGPT, have showcased significant prowess in natural language tasks, such as translating languages, constructing chatbots, and answering questions. When we consider biomedical data, we observe a resemblance to natural language in terms of sequences: biomedical literature and health records presented as text, biological sequences or sequencing data arranged in sequences, or sensor data like brain signals as time series. The question arises: Can we harness the potential of recent large language models to drive biomedical knowledge discoveries? In this survey, we will explore the application of large language models to three crucial categories of biomedical data: 1) textual data, 2) biological sequences, and 3) brain signals. Furthermore, we will delve into large language model challenges in biomedical research, including ensuring trustworthiness, achieving personalization, and adapting to multi-modal data representation

cs.CL↗

arXiv2024

On the positivity of Fourier transform of the stretched Gau{\ss}ian function

The stretched Gau{\ss}ian function $f(\mathbf{x})=\exp \left(-\|\mathbf{x}\|^s\right)$, as a real function defined on $\mathbb{R}^d$, has found numerous applications in mathematics and physics. For instance, to describe results from spectroscopy or inelastic scattering, the Fourier transform of the stretched Gau{\ss}ian function is needed. For $s \in(0,2]$, we prove that the Fourier transform of $f(\mathbf{x})=\exp \left(-\|\mathbf{x}\|^s\right)$ is everywhere positive on $\mathbb{R}^d$.

math.CA↗

arXiv2023

Topological conjugacy between Schneider's continued fraction map and a shift map on $\mathbb{Q}_p$

We prove that Schneider's continued fraction map is topologically conjugate to a shift map defined on $\mathbb{Q}_p$, and the topological conjugation $f\colon\mathbb{Q}_p \rightarrow \mathbb{Q}_p$ is an isometry such that $f(\mathbb{Q})=\mathbb{Z}[\frac{1}{p}]$. Furthermore, for $x \in \mathbb{Q}_p$ we proved that $x \in \mathbb{Q}$ if and only if $f(x) \in \mathbb{Z}[\frac{1}{p}]$.

math.DS↗

arXiv2023

XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision

Text classification aims to effectively categorize documents into pre-defined categories. Traditional methods for text classification often rely on large amounts of manually annotated training data, making the process time-consuming and labor-intensive. To address this issue, recent studies have focused on weakly-supervised and extremely weakly-supervised settings, which require minimal or no human annotation, respectively. In previous methods of weakly supervised text classification, pseudo-training data is generated by assigning pseudo-labels to documents based on their alignment (e.g., keyword matching) with specific classes. However, these methods ignore the importance of incorporating the explanations of the generated pseudo-labels, or saliency of individual words, as additional guidance during the text classification training process. To address this limitation, we propose XAI-CLASS, a novel explanation-enhanced extremely weakly-supervised text classification method that incorporates word saliency prediction as an auxiliary task. XAI-CLASS begins by employing a multi-round question-answering process to generate pseudo-training data that promotes the mutual enhancement of class labels and corresponding explanation word generation. This pseudo-training data is then used to train a multi-task framework that simultaneously learns both text classification and word saliency prediction. Extensive experiments on several weakly-supervised text classification datasets show that XAI-CLASS outperforms other weakly-supervised text classification methods significantly. Moreover, experiments demonstrate that XAI-CLASS enhances both model performance and explainability.

cs.CL↗

arXiv2023

TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answering

Table-based question answering (TableQA) is an important task in natural language processing, which requires comprehending tables and employing various reasoning ways to answer the questions. This paper introduces TableQAKit, the first comprehensive toolkit designed specifically for TableQA. The toolkit designs a unified platform that includes plentiful TableQA datasets and integrates popular methods of this task as well as large language models (LLMs). Users can add their datasets and methods according to the friendly interface. Also, pleasantly surprised using the modules in this toolkit achieves new SOTA on some datasets. Finally, \tableqakit{} also provides an LLM-based TableQA Benchmark for evaluating the role of LLMs in TableQA. TableQAKit is open-source with an interactive interface that includes visual operations, and comprehensive data for ease of use.

cs.CL↗

arXiv2023

Rational Variant of Hartogs' Theorem on Separate Holomorphicity

Given an uncountable algebraically closed field $K$, we proved that if partially defined function $f\colon K \times \dots \times K \dashrightarrow K$ defined on a Zariski open subset of the $n$-fold Cartesian product $K \times \dots \times K$ is rational in each coordinate whilst other coordinates are held constant, then $f$ is itself a rational function in $n$-variables.

math.AG↗

arXiv2021

Hausdorff Dimension and Lebesgue Measure of Codiagonal of Embedded Vector Bundles over Submanifolds in Euclidean Space

In this paper we study measure theoretical size of the image of naturally embedded vector bundles in $\mathbb{R}^{n} \times \mathbb{R}^{n}$ under the codiagonal morphism, i.e. $\Delta_{*}$ in the category of finite dimensional $\mathbb{R}$-vector spaces. Under very weak smoothness condition we show that codiagonal of normal bundles always contain an open subset of the ambient space, and we give corresponding criterions for the tangent bundles. For any differentiable hypersurface we show that the codiagonal of its tangent bundle has non-empty interior, unless the hypersurface is contained in a hyperplane. Assuming further smoothness (e.g. twice differentiable) we show that union of any family of hyperplanes that covers the hypersurface has maximal possible Hausdorff dimension. We also define and study a notion of degeneracy of embedded $C^{1}$ vector bundles over a $C^{1}$ submanifold and show as a corollary that if the base manifold has at least one non-inflection point then codiagonal of any $C^{1}$ line bundle over it has positive Lebesgue measure. Finally we show that codiagonal of any line bundle over an $n$-dimensional ellipsoid or a convex curve has non-empty interior, and the same assertion also holds for any non-tangent line bundle over a hyperplane.

math.MG↗

arXiv2021

Back-Projection Pipeline

We propose a simple extension of residual networks that works simultaneously in multiple resolutions. Our network design is inspired by the iterative back-projection algorithm but seeks the more difficult task of learning how to enhance images. Compared to similar approaches, we propose a novel solution to make back-projections run in multiple resolutions by using a data pipeline workflow. Features are updated at multiple scales in each layer of the network. The update dynamic through these layers includes interactions between different resolutions in a way that is causal in scale, and it is represented by a system of ODEs, as opposed to a single ODE in the case of ResNets. The system can be used as a generic multi-resolution approach to enhance images. We test it on several challenging tasks with special focus on super-resolution and raindrop removal. Our results are competitive with state-of-the-arts and show a strong ability of our system to learn both global and local image features.

eess.IV↗