arXiv subjects

Fang Wang

Publications and source records attributed to Fang Wang.

At least 73 records · Page 4Linked to original sources

arXiv2024

Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection

Most recent multispectral object detectors employ a two-branch structure to extract features from RGB and thermal images. While the two-branch structure achieves better performance than a single-branch structure, it overlooks inference efficiency. This conflict is increasingly aggressive, as recent works solely pursue higher performance rather than both performance and efficiency. In this paper, we address this issue by improving the performance of efficient single-branch structures. We revisit the reasons causing the performance gap between these structures. For the first time, we reveal the information interference problem in the naive early-fusion strategy adopted by previous single-branch structures. Besides, we find that the domain gap between multispectral images, and weak feature representation of the single-branch structure are also key obstacles for performance. Focusing on these three problems, we propose corresponding solutions, including a novel shape-priority early-fusion strategy, a weakly supervised learning method, and a core knowledge distillation technique. Experiments demonstrate that single-branch networks equipped with these three contributions achieve significant performance enhancements while retaining high efficiency. Our code will be available at \url{https://github.com/XueZ-phd/Efficient-RGB-T-Early-Fusion-Detection}.

cs.CV↗

arXiv2024

Enhancing Multistep Prediction of Multivariate Market Indices Using Weighted Optical Reservoir Computing

We propose and experimentally demonstrate an innovative stock index prediction method using a weighted optical reservoir computing system. We construct fundamental market data combined with macroeconomic data and technical indicators to capture the broader behavior of the stock market. Our approach shows significant higher performance than state-of-the-art methods such as linear regression, decision trees, and neural network architectures including long short-term memory. It captures well the market's high volatility and nonlinear behaviors despite limited data, demonstrating great potential for real-time, parallel, multi-dimensional data processing and predictions.

cs.LG↗

arXiv2024

Superpixel Semantics Representation and Pre-training for Vision-Language Task

The key to integrating visual language tasks is to establish a good alignment strategy. Recently, visual semantic representation has achieved fine-grained visual understanding by dividing grids or image patches. However, the coarse-grained semantic interactions in image space should not be ignored, which hinders the extraction of complex contextual semantic relations at the scene boundaries. This paper proposes superpixels as comprehensive and robust visual primitives, which mine coarse-grained semantic interactions by clustering perceptually similar pixels, speeding up the subsequent processing of primitives. To capture superpixel-level semantic features, we propose a Multiscale Difference Graph Convolutional Network (MDGCN). It allows parsing the entire image as a fine-to-coarse visual hierarchy. To reason actual semantic relations, we reduce potential noise interference by aggregating difference information between adjacent graph nodes. Finally, we propose a multi-level fusion rule in a bottom-up manner to avoid understanding deviation by mining complementary spatial information at different levels. Experiments show that the proposed method can effectively promote the learning of multiple downstream tasks. Encouragingly, our method outperforms previous methods on all metrics. Our code will be released upon publication.

cs.CV↗

arXiv2024

First Scan Search for Dark Photon Dark Matter with a Tunable Superconducting Radio-Frequency Cavity

Dark photons have emerged as promising candidates for dark matter, and their search is a top priority in particle physics, astrophysics, and cosmology. We report the first use of a tunable niobium superconducting radio-frequency cavity for a scan search of dark photon dark matter with innovative data analysis techniques. We mechanically adjusted the resonant frequency of a cavity submerged in liquid helium at a temperature of $2$ K, and scanned the dark photon mass over a frequency range of $1.37$ MHz centered at $1.3$ GHz. Our study leveraged the superconducting radio-frequency cavity's remarkably high quality factors of approximately $10^{10}$, resulting in the most stringent constraints to date on a substantial portion of the exclusion parameter space on the kinetic mixing coefficient $ε$ between dark photons and electromagnetic photons, yielding a value of $ε< 2.2 \times 10^{-16}$.

hep-ex↗

arXiv2024

Profiled Transfer Learning for High Dimensional Linear Model

We develop here a novel transfer learning methodology called Profiled Transfer Learning (PTL). The method is based on the \textit{approximate-linear} assumption between the source and target parameters. Compared with the commonly assumed \textit{vanishing-difference} assumption and \textit{low-rank} assumption in the literature, the \textit{approximate-linear} assumption is more flexible and less stringent. Specifically, the PTL estimator is constructed by two major steps. Firstly, we regress the response on the transferred feature, leading to the profiled responses. Subsequently, we learn the regression relationship between profiled responses and the covariates on the target data. The final estimator is then assembled based on the \textit{approximate-linear} relationship. To theoretically support the PTL estimator, we derive the non-asymptotic upper bound and minimax lower bound. We find that the PTL estimator is minimax optimal under appropriate regularity conditions. Extensive simulation studies are presented to demonstrate the finite sample performance of the new method. A real data example about sentence prediction is also presented with very encouraging results.

math.ST↗

arXiv2024

Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout

Goal-conditioned hierarchical reinforcement learning (HRL) presents a promising approach for enabling effective exploration in complex, long-horizon reinforcement learning (RL) tasks through temporal abstraction. Empirically, heightened inter-level communication and coordination can induce more stable and robust policy improvement in hierarchical systems. Yet, most existing goal-conditioned HRL algorithms have primarily focused on the subgoal discovery, neglecting inter-level cooperation. Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR), aiming to bridge inter-layer information synchronization and cooperation by exploiting forward dynamics. Firstly, the GCMR mitigates the state-transition error within off-policy correction via model-based rollout, thereby enhancing sample efficiency. Secondly, to prevent disruption by the unseen subgoals and states, lower-level Q-function gradients are constrained using a gradient penalty with a model-inferred upper bound, leading to a more stable behavioral policy conducive to effective exploration. Thirdly, we propose a one-step rollout-based planning, using higher-level critics to guide the lower-level policy. Specifically, we estimate the value of future states of the lower-level policy using the higher-level critic function, thereby transmitting global task information downwards to avoid local pitfalls. These three critical components in GCMR are expected to facilitate inter-level cooperation significantly. Experimental results demonstrate that incorporating the proposed GCMR framework with a disentangled variant of HIGL, namely ACLG, yields more stable and robust policy improvement compared to various baselines and significantly outperforms previous state-of-the-art algorithms.

cs.LG↗

arXiv2024

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.

cs.CV↗

arXiv2024

Homotopical Minimal Measures for Geodesic flows on Surfaces of Higher Genus

We study the homotopical minimal measures for positive definite autonomous Lagrangian systems. Homotopical minimal measures are action-minimizers in their homotopy classes, while the classical minimal measures (Mather measures) are action-minimizers in homology classes. Homotopical minimal measures are much more general, they are not necessarily homological action-minimizers. However, some of them can be obtained from the classical ones by lifting them to finite-fold covering spaces. We apply this idea of finite covering to the geodesic flows on surfaces of higher genus. Let $(M,G)$ be a compact closed surface with genus $g>1$, where $G$ is a complete Riemannian metric on $M$. Consider the positive definite autonomous Lagrangian $L(x,v)=G_x(v,v)$, whose Lagrangian system $ϕ_t: TM\rightarrow TM$ is exactly the complete geodesic flow on $TM$. We show that for each homotopical minimal ergodic measure $μ$ that is supported on a nontrivial simple closed periodic trajectory, there is a finite-fold covering space $M'$ such that each ergodic preimage of $μ$ on $TM'$ is a minimal measure in the classic Mather theory for the Lagrangian system on $TM'$.

math.DS↗

arXiv2024

Distributed Graph Embedding with Information-Oriented Random Walks

Graph embedding maps graph nodes to low-dimensional vectors, and is widely adopted in machine learning tasks. The increasing availability of billion-edge graphs underscores the importance of learning efficient and effective embeddings on large graphs, such as link prediction on Twitter with over one billion edges. Most existing graph embedding methods fall short of reaching high data scalability. In this paper, we present a general-purpose, distributed, information-centric random walk-based graph embedding framework, DistGER, which can scale to embed billion-edge graphs. DistGER incrementally computes information-centric random walks. It further leverages a multi-proximity-aware, streaming, parallel graph partitioning strategy, simultaneously achieving high local partition quality and excellent workload balancing across machines. DistGER also improves the distributed Skip-Gram learning model to generate node embeddings by optimizing the access locality, CPU throughput, and synchronization efficiency. Experiments on real-world graphs demonstrate that compared to state-of-the-art distributed graph embedding frameworks, including KnightKing, DistDGL, and Pytorch-BigGraph, DistGER exhibits 2.33x-129x acceleration, 45% reduction in cross-machines communication, and > 10% effectiveness improvement in downstream tasks.

cs.DC↗

arXiv2024

Obtaining the pseudoinverse solution of singular range-symmetric linear systems with GMRES-type methods

It is well known that for singular inconsistent range-symmetric linear systems, the generalized minimal residual (GMRES) method determines a least squares solution without breakdown. The reached least squares solution may be or not be the pseudoinverse solution. We show that a lift strategy can be used to obtain the pseudoinverse solution. In addition, we propose a new iterative method named RSMAR (minimum $\mathbf A$-residual) for range-symmetric linear systems $\mathbf A\mathbf x=\mathbf b$. At step $k$ RSMAR minimizes $\|\mathbf A\mathbf r_k\|$ in the $k$th Krylov subspace generated with $\{\mathbf A, \mathbf r_0\}$ rather than $\|\mathbf r_k\|$, where $\mathbf r_k$ is the $k$th residual vector and $\|\cdot\|$ denotes the Euclidean vector norm. We show that RSMAR and GMRES terminate with the same least squares solution when applied to range-symmetric linear systems. We provide two implementations for RSMAR. Our numerical experiments show that RSMAR is the most suitable method among GMRES-type methods for singular inconsistent range-symmetric linear systems.

math.NA↗

arXiv2024

GPBiLQ and GPQMR: Two iterative methods for unsymmetric partitioned linear systems

We introduce two iterative methods, GPBiLQ and GPQMR, for solving unsymmetric partitioned linear systems. The basic mechanism underlying GPBiLQ and GPQMR is a novel simultaneous tridiagonalization via biorthogonality that allows for short-recurrence iterative schemes. Similar to the biconjugate gradient method, it is possible to develop another method, GPBiCG, whose iterate (if it exists) can be obtained inexpensively from the GPBiLQ iterate. Whereas the iterate of GPBiCG may not exist, the iterates of GPBiLQ and GPQMR are always well defined as long as the biorthogonal tridiagonal reduction process does not break down. We discuss connections between the proposed methods and some existing methods, and give numerical experiments to illustrate the performance of the proposed methods.

math.NA↗

arXiv2023

Graph Neural Prompting with Large Language Models

Large language models (LLMs) have shown remarkable generalization capability with exceptional performance in various language modeling tasks. However, they still exhibit inherent limitations in precisely capturing and returning grounded knowledge. While existing work has explored utilizing knowledge graphs (KGs) to enhance language modeling via joint training and customized model architectures, applying this to LLMs is problematic owing to their large number of parameters and high computational cost. Therefore, how to enhance pre-trained LLMs using grounded knowledge, e.g., retrieval-augmented generation, remains an open question. In this work, we propose Graph Neural Prompting (GNP), a novel plug-and-play method to assist pre-trained LLMs in learning beneficial knowledge from KGs. GNP encompasses various designs, including a standard graph neural network encoder, a cross-modality pooling module, a domain projector, and a self-supervised link prediction objective. Extensive experiments on multiple datasets demonstrate the superiority of GNP on both commonsense and biomedical reasoning tasks across different LLM sizes and settings. Code is available at https://github.com/meettyj/GNP.

cs.CL↗

arXiv2023

Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning

Multiple defendants in a criminal fact description generally exhibit complex interactions, and cannot be well handled by existing Legal Judgment Prediction (LJP) methods which focus on predicting judgment results (e.g., law articles, charges, and terms of penalty) for single-defendant cases. To address this problem, we propose the task of multi-defendant LJP, which aims to automatically predict the judgment results for each defendant of multi-defendant cases. Two challenges arise with the task of multi-defendant LJP: (1) indistinguishable judgment results among various defendants; and (2) the lack of a real-world dataset for training and evaluation. To tackle the first challenge, we formalize the multi-defendant judgment process as hierarchical reasoning chains and introduce a multi-defendant LJP method, named Hierarchical Reasoning Network (HRN), which follows the hierarchical reasoning chains to determine criminal relationships, sentencing circumstances, law articles, charges, and terms of penalty for each defendant. To tackle the second challenge, we collect a real-world multi-defendant LJP dataset, namely MultiLJP, to accelerate the relevant research in the future. Extensive experiments on MultiLJP verify the effectiveness of our proposed HRN.

cs.CL↗

arXiv2023

Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher

Multiple Instance Learning (MIL) has demonstrated promise in Whole Slide Image (WSI) classification. However, a major challenge persists due to the high computational cost associated with processing these gigapixel images. Existing methods generally adopt a two-stage approach, comprising a non-learnable feature embedding stage and a classifier training stage. Though it can greatly reduce the memory consumption by using a fixed feature embedder pre-trained on other domains, such scheme also results in a disparity between the two stages, leading to suboptimal classification accuracy. To address this issue, we propose that a bag-level classifier can be a good instance-level teacher. Based on this idea, we design Iteratively Coupled Multiple Instance Learning (ICMIL) to couple the embedder and the bag classifier at a low cost. ICMIL initially fix the patch embedder to train the bag classifier, followed by fixing the bag classifier to fine-tune the patch embedder. The refined embedder can then generate better representations in return, leading to a more accurate classifier for the next iteration. To realize more flexible and more effective embedder fine-tuning, we also introduce a teacher-student framework to efficiently distill the category knowledge in the bag classifier to help the instance-level embedder fine-tuning. Thorough experiments were conducted on four distinct datasets to validate the effectiveness of ICMIL. The experimental results consistently demonstrate that our method significantly improves the performance of existing MIL backbones, achieving state-of-the-art results. The code is available at: https://github.com/Dootmaan/ICMIL/tree/confidence_based

cs.CV↗

arXiv2023

DxHash: A Scalable Consistent Hash Based on the Pseudo-Random Sequence

Consistent hashing (CH) has been pivotal as a data router and load balancer in diverse fields, including distributed databases, cloud infrastructure, and peer-to-peer networks. However, existing CH algorithms often fall short in simultaneously meeting various critical requirements, such as load balance, minimal disruption, statelessness, high lookup rate, small memory footprint, and low update overhead. To address these limitations, we introduce DxHash, a scalable consistent hashing algorithm based on pseudo-random sequences. To adjust workloads on heterogeneous nodes and enhance flexibility, we propose weighted DxHash. Through comprehensive evaluations, DxHash demonstrates substantial improvements across all six requirements compared to state-of-the-art alternatives. Notably, even when confronted with a 50% failure ratio in a cluster of one million nodes, DxHash maintains remarkable processing capabilities, handling up to 13.3 million queries per second.

cs.DS↗

arXiv2023

WLFC: Write Less in Flash-based Cache

Flash-based disk caches, for example Bcache and Flashcache, has gained tremendous popularity in industry in the last decade because of its low energy consumption, non-volatile nature and high I/O speed. But these cache systems have a worse write performance than the read performance because of the asymmetric I/O costs and the the internal GC mechanism. In addition to the performance issues, since the NAND flash is a type of EEPROM device, the lifespan is also limited by the Program/Erase (P/E) cycles. So how to improve the performance and the lifespan of flash-based caches in write-intensive scenarios has always been a hot issue. Benefiting from Open-Channel SSDs (OCSSDs), we propose a write-friendly flash-based disk cache system, which is called WLFC (Write Less in the Flash-based Cache). In WLFC, a strictly sequential writing method is used to minimize the write amplification. A new replacement algorithm for the write buffer is designed to minimize the erase count caused by the evicting. And a new data layout strategy is designed to minimize the metadata size persisted in SSDs. As a result, the Over-Provisioned (OP) space is completely removed, the erase count of the flash is greatly reduced, and the metadata size is 1/10 or less than that in BCache. Even with a small amount of metadata, the data consistency after the crash is still guaranteed. Compared with the existing mechanism, WLFC brings a 7%-80% reduction in write latency, a 1.07*-4.5* increment in write throughput, and a 50%-88.9% reduction in erase count, with a moderate overhead in read performance.

cs.OS↗

arXiv2023

Mixture Conditional Regression with Ultrahigh Dimensional Text Data for Estimating Extralegal Factor Effects

Testing judicial impartiality is a problem of fundamental importance in empirical legal studies, for which standard regression methods have been popularly used to estimate the extralegal factor effects. However, those methods cannot handle control variables with ultrahigh dimensionality, such as found in judgment documents recorded in text format. To solve this problem, we develop a novel mixture conditional regression (MCR) approach, assuming that the whole sample can be classified into a number of latent classes. Within each latent class, a standard linear regression model can be used to model the relationship between the response and a key feature vector, which is assumed to be of a fixed dimension. Meanwhile, ultrahigh dimensional control variables are then used to determine the latent class membership, where a Naïve Bayes type model is used to describe the relationship. Hence, the dimension of control variables is allowed to be arbitrarily high. A novel expectation-maximization algorithm is developed for model estimation. Therefore, we are able to estimate the interested key parameters as efficiently as if the true class membership were known in advance. Simulation studies are presented to demonstrate the proposed MCR method. A real dataset of Chinese burglary offenses is analyzed for illustration purpose.

stat.ME↗

arXiv2023

A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare

Reinforcement learning (RL) has emerged as a powerful approach for tackling complex medical decision-making problems such as treatment planning, personalized medicine, and optimizing the scheduling of surgeries and appointments. It has gained significant attention in the field of Natural Language Processing (NLP) due to its ability to learn optimal strategies for tasks such as dialogue systems, machine translation, and question-answering. This paper presents a review of the RL techniques in NLP, highlighting key advancements, challenges, and applications in healthcare. The review begins by visualizing a roadmap of machine learning and its applications in healthcare. And then it explores the integration of RL with NLP tasks. We examined dialogue systems where RL enables the learning of conversational strategies, RL-based machine translation models, question-answering systems, text summarization, and information extraction. Additionally, ethical considerations and biases in RL-NLP systems are addressed.

cs.CL↗