检索结果-内蒙古大学图书馆

On the Adversarial Robustness of Graph Contrastive Learning Methods

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guerranti, Filippo Yi, Zinuo Starovoit, Anna Kamel, Rafiq Geisler, Simon Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Contrastive learning (CL) has emerged as a powerful framework for learning representations of images and text in a self-supervised manner while enhancing model robustness against adversarial attacks. More recently, researchers have extended the principles of contrastive learning to graph-structured data, giving birth to the field of graph contrastive learning (GCL). However, whether GCL methods can deliver the same advantages in adversarial robustness as their counterparts in the image and text domains remains an open question. In this paper, we introduce a comprehensive robustness evaluation protocol tailored to assess the robustness of GCL models. We subject these models to adaptive adversarial attacks targeting the graph structure, specifically in the evasion scenario. We evaluate node and graph classification tasks using diverse real-world datasets and attack strategies. With our work, we aim to offer insights into the robustness of GCL methods and hope to open avenues for potential future research directions. © 2023, CC BY.

关键词： Graphic methods

Uncertainty Estimation for Molecules: Desiderata and Methods

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wollschläger, Tom Gao, Nicholas Charpentier, Bertrand Ketata, Mohamed Amine Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Graph Neural networks (GNNs) are promising surrogates for quantum mechanical calculations as they establish unprecedented low errors on collections of molecular dynamics (MD) trajectories. Thanks to their fast inference times they promise to accelerate computational chemistry applications. Unfortunately, despite low in-distribution (ID) errors, such GNNs might be horribly wrong for out-of-distribution (OOD) samples. Uncertainty estimation (UE) may aid in such situations by communicating the model’s certainty about its prediction. Here, we take a closer look at the problem and identify six key desiderata for UE in molecular force fields, three ‘physics-informed’ and three ‘application-focused’ ones. To overview the field, we survey existing methods from the field of UE and analyze how they fit to the set desiderata. By our analysis, we conclude that none of the previous works satisfies all criteria. To fill this gap, we propose Localized Neural Kernel (LNK) a Gaussian Process (GP)-based extension to existing GNNs satisfying the desiderata. In our extensive experimental evaluation, we test four different UE with three different backbones and two datasets. In out-of-equilibrium detection, we find LNK yielding up to 2.5 and 2.1 times lower errors in terms of AUC-ROC score than dropout or evidential regression-based methods while maintaing high predictive performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Errors

REVISITING ROBUSTNESS IN GRAPH MACHINE LEARNING

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gosch, Lukas Sturm, Daniel Geisler, Simon Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Many works show that node-level predictions of Graph Neural networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: i) for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption;ii) surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs significantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node. 1 © 2023, CC BY.

关键词： Graph neural networks

Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Schuchardt, Jan Scholten, Yan Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

A machine learning model is traditionally considered robust if its prediction remains (almost) constant under input perturbations with small norm. However, real-world tasks like molecular property prediction or point cloud segmentation have inherent equivariances, such as rotation or permutation equivariance. In such tasks, even perturbations with large norm do not necessarily change an input’s semantic content. Furthermore, there are perturbations for which a model’s prediction explicitly needs to change. For the first time, we propose a sound notion of adversarial robustness that accounts for task equivariance. We then demonstrate that provable robustness can be achieved by (1) choosing a model that matches the task’s equivariances (2) certifying traditional adversarial robustness. Certification methods are, however, unavailable for many models, such as those with continuous equivariances. We close this gap by developing the framework of equivariance-preserving randomized smoothing, which enables architecture-agnostic certification. We additionally derive the first architecture-specific graph edit distance certificates, i.e. sound robustness guarantees for isomorphism equivariant tasks like node classification. Overall, a sound notion of robustness is an important prerequisite for future work at the intersection of robust and geometric machine learning. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

Optimized data Storage Algorithm of IoT Based on Cloud Computing in Distributed System

学校读者我要写书评

暂无评论

Optimized Data Storage Algorithm of IoT Based on Cloud Compu...

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Deepthi, K.Jaya Balakrishnan, T.Suresh Krishnan, Prabhakar Ebenezar, U.Samson Nageshwari Mohan Babu University Department of Aiml AP Tirupati India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Amrita Vishwa Vidyapeetham Center for Cyber Security Systems and Networks Amritapuri-campus India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy620009 India

ISBN: (纸本)9798350373783

IoT and cloud technology are vital for large systems. An improved data storage technique for IoT applications and cloud distribution is described in this research. Scalability, reliability, latency, and resource usage are internal and external to the algorithm. The approach above scales well with work portion or dataset size. The first experiment shows the algorithm scaling perfectly even as IoT devices generate additional data. Experiment 2 proves linear scalability works for 100,000 IoT devices, while Experiment 3 efficiently organizes 1 million data points. It proved the algorithm by tolerating manufactured faults. To ensure data service availability, Experiment 1 tests the system's operational dependability on node failures and network disturbances. With 0.1% downtime even under challenging conditions, experiment 2 showed the algorithm's incredible robustness in real-world applications. To improve data organization, this experiment exhibits data consistency when nodes fail. Lower and constant time improves operation safety and reliability. Algorithm 1 shows how the algorithm can quickly answer data queries and keep up with the massive amount of data transfers, supporting low-latency IoT applications. Average data retrieval latency of experiment 2 is 10 ms, which is real-time for vital information. Trial 3 processes data online with a latency © 2024 IEEE.

关键词： Cloud storage

Generalizing Neural Wave Functions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gao, Nicholas Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany

Recent neural network-based wave functions have achieved state-of-the-art accuracies in modeling ab-initio ground-state potential energy surface. However, these networks can only solve different spatial arrangements of the same set of atoms. To overcome this limitation, we present Graph-learned Orbital Embeddings (Globe), a neural network-based reparametrization method that can adapt neural wave functions to different molecules. Globe learns representations of local electronic structures that generalize across molecules via spatial message passing by connecting molecular orbitals to covalent bonds. Further, we propose a size-consistent wave function Ansatz, the Molecular Orbital Network (Moon), tailored to jointly solve Schrödinger equations of different molecules. In our experiments, we find Moon converging in 4.5 times fewer steps to similar accuracy as previous methods or to lower energies given the same time. Further, our analysis shows that Moon’s energy estimate scales additively with increased system sizes, unlike previous work where we observe divergence. In both computational chemistry and machine learning, we are the first to demonstrate that a single wave function can solve the Schrödinger equation of molecules with different atoms jointly. © 2023, CC BY.

关键词： Molecular orbitals

Machine Learning-Enhanced Analysis of Genomic data for Precision Medicine

学校读者我要写书评

暂无评论

Machine Learning-Enhanced Analysis of Genomic Data for Preci...

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Sasikala, R. Deepthi, K. Jaya Balakrishnan, T. Suresh Krishnan, Prabhakar Ebenezar, U. Samson Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy620009 India Mohan Babu University Department of Aiml Ap Tirupati India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Amrita Vishwa Vidyapeetham Center for Cyber Security Systems and Networks Amritapuri-Campus India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350373783

Precision medicine employs genetic data, which is enhanced with machine learning algorithms, to determine the most relevant treatment method per patient's genotype. We have zoned in on the area of a machine learning-guided genetic information analysis in this study to assist in clinical decisionmaking of precision medicine while improvising. Genetic information for 500 cancer patients cases taken from the public database and cleaned to lean out the desired features were furnished. Different machine learning algorithms were trained, including SVM, random forest, gradient boost, deep learning (CNN) and ensemble (ensemble method). Their performance was investigated for predicting cancer subtypes. The ensemble model reached the top accuracy level (88%), the best sensitivity (85%), ever specificity (91%) and AUC score (0.95). By comparison a group had better result than an individual algorithm could across all metrics. In further, deep learning methods were reported to attain more accuracy and F1 scores which is more than traditional machine learning methods. These findings hence prequalify the usefulness of ML in investigating genotype data in precision medicine, and enable physicians with useful information to select treatment options, make prognosis, and indicate the medical care. © 2024 IEEE.

关键词： Adversarial machine learning

Dynamic Topology Management In Ad-Hoc networks For Improved Performance 2

学校读者我要写书评

暂无评论

Dynamic Topology Management In Ad-Hoc Networks For Improved ...

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Anakath, A.S. Kannadasan, R. Margarat, G. Simi Pandian, A. Pasumpon Antony Sibiya Varghese, V. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology VIT University Tamil Nadu Vellore India Department of Computer Science and Engineering New Prince Shri Bhavani College of Engineering and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering CARE College of Engineering Trichy India Department of Artificial Intelligence and Data Science GRT Institute of Engineering and Technology Tamil Nadu Tiruttani India

ISBN: (纸本)9798350383867

Optimization in ad hoc networks is a highly specialized task because the structure of the network is loosely formed, and each node is independently responsible for its operation. In order to obtain a better result from this solely formed networks this report offer extensive Dynamic Topology Management (DTM) method. Dynamic routing protocols lager lines, dividend balancing, Life-saving administration, guarantee of reliability, cross-layer design, security aspects and the on-time monitoring and discovery of topology changes are the main objectives and steps to be accomplished. Real-time Location monitoring and forest structure discovery are made possible by employing adaptive routing protocols, namely Dynamic Source Routing(DSR) and Ad-Hoc On-Demand Distance Vector(AODV). Also, the algorithms are capable of making advance adjustments to routing routes and resource allocations drawn from the mobility patterns forecasting which is vital. Load balancing methods, which distribute traffic in a network evenly, enable the system to run efficiently and avoid problems caused by overloading. Algorithms that are energy-efficient and make the best use of energy resources having their topology's optimized are introduced to the streamlined energy distribution systems. These algorithms are focused on the node's energy level. Through fault tolerance techniques which recognize and handle failures in nodes and partitioned networks, connectedness activity is a continuous one. Through QoS perception, the network topology might automatically be tailored to conform to the given quality criteria, thus not restricting the choice for differing applications. The proposed could have defenses against adversary nodes and their potential DDoS attacks which will enhance network protection. Yet another advantage of an architectural style that promotes cross-layer collaboration is enhanced topology management which is the goal around which the functions of various levels of the protocol stack revolve

关键词： Decision making

Medical Entity Disambiguation with Medical Mention Relation and Fine-grained Entity Knowledge 30

学校读者我要写书评

暂无评论

Medical Entity Disambiguation with Medical Mention Relation ...

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Lu, Wenpeng Zhang, Guobiao Peng, Xueping Guan, Hongjiao Wang, Shoujin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia Data Science Institute University of Technology Sydney Sydney Australia Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9782493814104

Medical entity disambiguation (MED) plays a crucial role in natural language processing and biomedical domains, which is the task of mapping ambiguous medical mentions to structured candidate medical entities from knowledge bases (KBs). However, existing methods for MED often fail to fully utilize the knowledge within medical KBs and overlook essential interactions between medical mentions and candidate entities, resulting in knowledge- and interaction-inefficient modeling and suboptimal disambiguation performance. To address these limitations, this paper proposes a novel approach, MED with Medical Mention Relation and Fine-grained Entity Knowledge (MMR-FEK). Specifically, MMR-FEK incorporates a mention relation fusion module and an entity knowledge fusion module, followed by an interaction module. The former employs a relation graph convolutional network to fuse mention relation information between medical mentions to enhance mention representations, while the latter leverages an attention mechanism to fuse synonym and type information of candidate entities to enhance entity representations. Afterwards, an interaction module is designed to employ a bidirectional attention mechanism to capture interactions between medical mentions and entities to generate the matching representation. Extensive experiments on two publicly available real-world datasets demonstrate MMR-FEK's superiority over state-of-the-art(SOTA) MED baselines across all metrics. Our source code is publicly available. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Natural language processing systems