检索结果-内蒙古大学图书馆

Improving Molecular Graph Generation with Flow Matching and Optimal Transport

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hou, Xiaoyang Zhu, Tian Ren, Milong Bu, Dongbo Gao, Xin Zhang, Chunming Sun, Shiwei Key Laboratory of Intelligent Information Processing Institute of Computing Technology School of Computer Science and Technology University of Chinese Academy of Sciences China Central China Research Institute for Artificial Intelligence Technologies China Western Institute of Computing Technology Phil Rivers Technology King Abdullah University of Science and Technology Saudi Arabia

Generating molecular graphs is crucial in drug design and discovery but remains challenging due to the complex interdependencies between nodes and edges. While diffusion models have demonstrated their potentiality in molecular graph design, they often suffer from unstable training and inefficient sampling. To enhance generation performance and training stability, we propose GGFlow, a discrete flow matching generative model incorporating optimal transport for molecular graphs and it incorporates an edge-augmented graph transformer to enable the direct communications among chemical bounds. Additionally, GGFlow introduces a novel goal-guided generation framework to control the generative trajectory of our model, aiming to design novel molecular structures with the desired properties. GGFlow demonstrates superior performance on both unconditional and conditional molecule generation tasks, outperforming existing baselines and underscoring its effectiveness and potential for wider application. © 2024, CC BY.

关键词： Molecular docking

An Evolutionary Multi-Objective Neural Architecture Search Approach to Advancing Cognitive Diagnosis in intelligent Education

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Yang, Shangshang Ma, Haiping Bi, Ying Tian, Ye Zhang, Limiao Jin, Yaochu Zhang, Xingyi School of Artificial Intelligence Anhui University Hefei China Institutes of Physical Science and Information Technology Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China School of Electrical and Information Engineering Computational Intelligence Laboratory Zhengzhou University Zhengzhou China School of Computer Science and Technology Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei Anhui China School of Engineering Westlake University Hangzhou China

As a pivotal technique in intelligent education systems, cognitive diagnosis (CD) serves to reveal students’ knowledge proficiency for better tackling subsequent tasks. Unfortunately, due to pursuing high model interpretability, existing manually designed models for CD often hold simplistic architectures, which cannot cope with intricate data in modern education platforms. Furthermore, the bias of human design limits the emergence of novel and effective CD models. To develop interpretable and more effective models, thus this paper proposes an evolutionary multi-objective neural architecture search (NAS) approach for CD. Specifically, we first adopt a comprehensive search space for the NAS task of CD: all candidate models can be encompassed by a general model that deals with three distinct types of inputs. Then, an innovative model interpretability objective is devised to formulate the architecture search task as a bi-objective optimization problem (BOP). To solve the BOP, we employ a multi-objective genetic programming (MOGP) as the search strategy to explore the search space. To make the employed MOGP search well, all architectures are first encoded by trees for easy optimization, and we devise a genetic operation and a population initialization strategy to expedite its convergence. Finally, the proposed approach is actually a MOGP-based NAS approach for CD. Extensive experiments show that CD models searched by the proposed approach exhibit significantly better performance than existing models and hold as good interpretability as handcrafted models. Besides, the effectiveness of the proposed MOGP search strategy, the devised objective, and tailored strategies are validated. IEEE

关键词： Computer architecture

MOSMOS: Multi-organ segmentation facilitated by medical report supervision

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tian, Weiwei Huang, Xinyu Hou, Junlin Ren, Caiyue Jiang, Longquan Zhao, Rui-Wei Jin, Gang Zhang, Yuejie Geng, Daoying Academy for Engineering and Technology Fudan University Shanghai200433 China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Shanghai200433 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Owing to a large amount of multi-modal data in modern medical systems, such as medical images and reports, Medical Vision-Language Pre-training (Med-VLP) has demonstrated incredible achievements in coarse-grained downstream tasks (i.e., medical classification, retrieval, and visual question answering). However, the problem of transferring knowledge learned from Med-VLP to fine-grained multi-organ segmentation tasks has barely been investigated. Multi-organ segmentation is challenging mainly due to the lack of large-scale fully annotated datasets and the wide variation in the shape and size of the same organ between individuals with different diseases. In this paper, we propose a novel pre-training & fine-tuning framework for Multi-Organ Segmentation by harnessing Medical repOrt Supervision (MOSMOS). Specifically, we first introduce global contrastive learning to maximally align the medical image-report pairs in the pre-training stage. To remedy the granularity discrepancy, we further leverage multi-label recognition to implicitly learn the semantic correspondence between image pixels and organ tags. More importantly, our pre-trained models can be transferred to any segmentation model by introducing the pixel-tag attention maps. Different network settings, i.e., 2D U-Net and 3D UNETR, are utilized to validate the generalization. We have extensively evaluated our approach using different diseases and modalities on BTCV, AMOS, MMWHS, and BRATS datasets. Experimental results in various settings demonstrate the effectiveness of our framework. This framework can serve as the foundation to facilitate future research on automatic annotation tasks under the supervision of medical reports. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Evolutionary Multi-Objective Neural Architecture Search for Generalized Cognitive Diagnosis Models

学校读者我要写书评

暂无评论

Evolutionary Multi-Objective Neural Architecture Search for ...

Data-driven Optimization of Complex Systems (DOCS), International Conference on

作者： Shangshang Yang Cheng Zhen Ye Tian Haiping Ma Yuanchao Liu Panpan Zhang Xingyi Zhang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

Cognitive diagnosis models (CDMs) with high generalization are essential for intelligent education systems to reveal students' knowledge states in multiple datasets. However, existing CDMs' architectures are designed dependent on researcher expertise and experience from observing and summarizing partial students' learning behaviors, which makes handcrafted models not cover all learning behaviors well and thus limits their generalization. To develop generalized CDMs, this paper proposes an evolutionary neural architecture search to design CDMs' architectures effective on multiple datasets automatically. Specifically, we first formulate the search task as a multi-objective optimization problem (MOP), which maximizes model performance on multiple datasets containing learning behaviors as many as possible to ensure model generalization. Then, an expressive search space is devised to contain as many potential architectures as possible, where each architecture is denoted by a unified form, taking three given inputs and integrating them in a linear or no-linear manner for prediction. Finally, an evolutionary algorithm with a tailored deduplication strategy is employed to solve the MOP, where each architecture is further represented by a single-root computation tree for easy optimization. Experiments on multiple datasets demonstrate the generalization and effectiveness of the best architecture searched by the proposed approach, and the searched architecture also holds as good interpretability as handcrafted architectures.

关键词：

Learning to Learn Transferable Generative Attack for Person Re-Identification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan College of Electrical and Information Engineering Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology Hunan Changsha China College of Information Science and Engineering Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Changsha China

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. The source codes are available at https://***/yuanbianGit/MTGA. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

Quasiperiodic Symmetric Tilt FCC Grain Boundaries

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zou, Wenwen Zhang, Juan Xu, Jie Jiang, Kai Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China LSEC NCMIS Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

In this work, we investigate [110] symmetric tilt FCC grain boundaries (GBs) by a recently developed approach for quasiperiodic interfaces using the Landau-Brazovskii model. On special tilt angles associated with quadratic algebraic numbers, quasiperiodic GBs exhibit generalized Fibonacci substitution rules. The transition mechanism from quasiperiodic GBs to periodic GBs is explored through sphere offsets and spectral coalescence. We also propose an accurate method to calculate the GB energy for arbitrary tilt angle and analyze the factors affecting the GB energy. The revealing GB energy change is continue along with tilt angle except periodic GBs. © 2024, CC BY-NC-SA.

关键词： Grain boundaries

Generalized Self-Adaption Network for Domain Adaptation

学校读者我要写书评

暂无评论

Generalized Self-Adaption Network for Domain Adaptation

Artificial Intelligence and intelligent information processing (AIIIP), International Conference on

作者： Yongheng Bian Xiao Ke Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou China

The purpose of domain adaptation is to transfer knowledge learned in the labeled source domain to unlabeled but related target domains without requiring a large number of target domain labels. The latest method of domain adaptation mainly adjusts the distribution of the source and target domains to adapt to the target domain. Despite significant success, when there are significant distribution differences between the source and target domains, the adaptability in the target domain still decreases, which may be due to insufficient exploration of domain specific features leading to domain offset issues. To address this issue, we propose the GSA-NET framework in this article. We designed an adversarial dropout method to improve the generalization performance of the model in the target domain by pushing the decision boundary away from the feature dense region. At the same time, in order to effectively match the distribution of advanced features across domains, we deploy feature adaptation modules before the classification layer, which can significantly reduce domain differences. Our experiments on two cross domain benchmarks, Office Home and Office-31, have shown that the proposed method is significantly superior to existing methods.

关键词：

Non-autoregressive Streaming Transformer for Simultaneous Translation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Zhengrui Zhang, Shaolei Guo, Shoutao Shao, Chenze Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Future Science and Engineering Soochow University China

Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality. However, training these models to achieve high quality while maintaining low latency often leads to a tendency for aggressive anticipation. We argue that such issue stems from the autoregressive architecture upon which most existing SiMT models are built. To address those issues, we propose non-autoregressive streaming Transformer (NAST) which comprises a unidirectional encoder and a non-autoregressive decoder with intra-chunk parallelism. We enable NAST to generate the blank token or repetitive tokens to adjust its READ/WRITE strategy flexibly, and train it to maximize the non-monotonic latent alignment with an alignment-based latency loss. Experiments on various SiMT benchmarks demonstrate that NAST outperforms previous strong autoregressive SiMT baselines. Source code is publicly available at https://***/ictnlp/NAST. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine translation

Analogical Learning for Cross-Scenario Generalization: Framework and Application to intelligent Localization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Zirui Zhang, Zhaoyang Xing, Ziqing Li, Ridong Yang, Zhaohui Jin, Richeng Huang, Chongwen Yang, Yuzhi Debbah, Mérouane College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Multi-modal Communication Networks and Intelligent Information Processing Hangzhou310027 China College of Computing and Mathematical Sciences Khalifa University Abu Dhabi999041 United Arab Emirates

Existing learning models often exhibit poor generalization when deployed across diverse scenarios. It is mainly due to that the underlying reference frame of the data varies with the deployment environment and settings. However, despite the data of each scenario has its distinct reference frame, its generation generally follows the same underlying physical rule. Based on these findings, this article proposes a brand-new universal deep learning framework named analogical learning (AL), which provides a highly efficient way to implicitly retrieve the reference frame information associated with a scenario and then to make accurate prediction by relative analogy across scenarios. Specifically, an elegant bipartite neural network architecture called Mateformer is designed, the first part of which calculates the relativity within multiple feature spaces between the input data and a small amount of embedded data from the current scenario, while the second part uses these relativity to guide the nonlinear analogy. We apply AL to the typical multi-scenario learning problem of intelligent wireless localization in cellular networks. Extensive experiments show that AL achieves state-of-the-art accuracy, stable transferability and robust adaptation to new scenarios without any tuning, and outperforming conventional methods with a precision improvement of nearly two orders of magnitude. All data and code are available at https://***/ziruichen-research/ALLoc. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep learning