检索结果-内蒙古大学图书馆

Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tagasovska, Nataša Park, Ji Won Kirchmeyer, Matthieu Frey, Nathan C. Watkins, Andrew Martin Ismail, Aya Abdelsalam Jamasb, Arian Rokkum Lee, Edith Bryson, Tyler Ra, Stephen Cho, Kyunghyun Prescient Design Genentech United States Department of Computer Science Center for Data Science New York University United States

Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model predicting the target property of interest. The model predictions are used to determine which designs to evaluate in the lab, and the model is updated on the new measurements to inform the next cycle of decisions. A key challenge is that the experimental feedback from each cycle inspires changes in the candidate proposal or experimental protocol for the next cycle, which lead to distribution shifts. To promote robustness to these shifts, we must account for them explicitly in the model training. We apply domain generalization (DG) methods to classify the stability of interactions between an antibody and antigen across five domains defined by design cycles. Our results suggest that foundational models and ensembling improve predictive performance on out-of-distribution domains. We publicly release our codebase extending the DG benchmark "DomainBed," and the associated dataset of antibody sequences and structures emulating distribution shifts across design cycles. © 2024, CC BY-NC-SA.

关键词：

Adjoint-Free 4D-Var Methods Via Line Search Optimization For Non-Linear data Assimilation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nino-Ruiz, Elias D. Diaz-Rodriguez, Jairo Applied Math and Computer Science Laboratory Department of Computer Science Universidad del Norte Colombia Department of Mathematics and Statistics York University Canada

This paper proposes two practical implementations of Four-Dimensional Variational (4D-Var) Ensemble Kalman Filter (4D-EnKF) methods for non-linear data assimilation. Our formulations' main idea is to avoid the intrinsic need for adjoint models in the context of 4D-Var optimization and, even more, to handle non-linear observation operators during the assimilation of observations. The proposed methods work as follows: snapshots of an ensemble of model realizations are taken at observation times, these snapshots are employed to build control spaces onto which analysis increments can be estimated. Via the linearization of observation operators at observation times, a line-search based optimization method is proposed to estimate optimal analysis increments. The convergence of this method is theoretically proven as long as the dimension of control-spaces equals model one. In the first formulation, control spaces are given by full-rank square root approximations of background error covariance matrices via the Bickel and Levina precision matrix estimator. In this context, we propose an iterative Woodbury matrix formula to perform the optimization steps efficiently. The last formulation can be considered as an extension of the Maximum Likelihood Ensemble Filter to the 4D-Var context. This employs pseudo-square root approximations of prior error covariance matrices to build control spaces. Experimental tests are performed by using the Lorenz 96 model. The results reveal that, in terms of Root-Mean-Square-Error values, both methods can obtain reasonable estimates of posterior error modes in the 4D-Var optimization problem. Moreover, the accuracies of the proposed filter implementations can be improved as the ensemble sizes are increased. © 2023, CC BY.

关键词： Optimization

RPR-Net: A Point Cloud-Based Rotation-Aware Large Scale Place Recognition Network 17th

学校读者我要写书评

暂无评论

RPR-Net: A Point Cloud-Based Rotation-Aware Large Scale Plac...

17th European Conference on computer Vision, ECCV 2022

作者： Fan, Zhaoxin Song, Zhenbo Zhang, Wenping Liu, Hongyan He, Jun Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Department of Management Science and Engineering Tsinghua University Beijing100084 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (纸本)9783031250552

Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, previous methods have made delightful achievements. However, how to deal with catastrophic collapse caused by rotation problems is still under-explored. In this paper, to tackle the issue, we propose a novel Point Cloud-based Rotation-aware Large Scale Place Recognition Network (RPR-Net). In particular, to solve the problem, we propose to learn rotation-invariant features in three steps. First, we design three kinds of novel Rotation-Invariant Features (RIFs), which are low-level features that can hold the rotation-invariant property. Second, using these RIFs, we design an attentive module to learn rotation-invariant kernels. Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process. By doing so, high-level scene-specific rotation-invariant features can be learned. We call the above process an Attentive Rotation-Invariant Convolution (ARIConv). To achieve the place recognition goal, we build RPR-Net, which takes ARIConv as a basic unit to construct a dense network architecture. Then, powerful global descriptors used for retrieval-based place recognition can be sufficiently extracted from RPR-Net. Experimental results on prevalent datasets show that our method achieves comparable results to existing state-of-the-art place recognition models and significantly outperforms other rotation-invariant baseline models when solving rotation problems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Network architecture

Framework to generate hypergraphs with community structure

学校读者我要写书评

暂无评论

Physical Review E 2024年第3期109卷 034309-034309页

作者： Nicolò Ruggeri Federico Battiston Caterina De Bacco Max Planck Institute for Intelligent Systems Cyber Valley 72076 Tübingen Germany Department of Computer Science ETH 8004 Zürich Switzerland Department of Network and Data Science Central European University 1100 Vienna Austria

In recent years hypergraphs have emerged as a powerful tool to study systems with multibody interactions which cannot be trivially reduced to pairs. While highly structured methods to generate synthetic data have proved fundamental for the standardized evaluation of algorithms and the statistical study of real-world networked data, these are scarcely available in the context of hypergraphs. Here we propose a flexible and efficient framework for the generation of hypergraphs with many nodes and large hyperedges, which allows specifying general community structures and tune different local statistics. We illustrate how to use our model to sample synthetic data with desired features (assortative or disassortative communities, mixed or hard community assignments, etc.), analyze community detection algorithms, and generate hypergraphs structurally similar to real-world data. Overcoming previous limitations on the generation of synthetic hypergraphs, our work constitutes a substantial advancement in the statistical modeling of higher-order systems.

关键词： Clustering Community structure Network formation & growth Network structure Patterns in complex systems

A Semiconductor Manufacturing Final Test Yield Classification Using Random Forest 2

学校读者我要写书评

暂无评论

A Semiconductor Manufacturing Final Test Yield Classificatio...

2nd International Conference on data science and Information System, ICDSIS 2024

作者： Dineshkumar, R. Aluvala, Srinivas Srinath, Suma Alsalami, Zaid Krishnaprasath, V.T. Saveetha Institute Of Medical And Technical Sciences Saveetha University Saveetha School Of Engineering Department Of Ece Chennai India Sr University School Of Computer Science And Engineering Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Aiml Bengaluru India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Nehru Institute Of Engineering And Technology Department Of Artificial Intelligence And Data Science Coimbatore India

ISBN: (纸本)9798350381665

Semi-conductor manufacturing companies are growing rapidly by forming collaborative design and wafer fabrication. The yield prediction techniques use production data and provide improved operational efficiency and decrease production costs. Random forest classification method is proposed for semiconductor manufacturing Final Test (FT) yield prediction. data pre-processing methods include Gaussian mixture Model, one hot encoder and Label encoder whereas improved grid search algorithm is used for feature selection. The selected features are then given to the implemented classification Random forest (RF) model. The RF method was evaluated by conducting experiments for three different products which are provided by Silicon Laboratories. The RF method outperformed in handling both numerical and categorical production data and is evaluated by the metrics such as accuracy, precision, recall and F-measure. The developed method achieved 0.985 of accuracy when compared with the existing methods such as LSTM-AM and SH-DNN. © 2024 IEEE.

关键词： Gaussian distribution

Automatic Smart Crawling on Twitter for Weather Information in Indonesia 8

学校读者我要写书评

暂无评论

Automatic Smart Crawling on Twitter for Weather Information ...

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Purwandari, Kartika Perdana, Reza Bayu Sigalingging, Join W.C. Rahutomo, Reza Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Database Center Division of BMKG Meteorological Climatological and Geophysical Agency Jakarta10720 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Although Twitter is a popular platform for social interaction analysis and text data mining, it faces challenges with geolocation automation. To address this problem, the researchers propose the utilization of a Support Vector Machine (SVM) model to develop an automated Twitter crawling system. The system aims to collect data related to weather in Indonesia by employing Twin, a Python-based Twitter scraping software. To overcome null geolocations, the study incorporates aliases created based on the common practice of Indonesian users mentioning the country's location in tweets. The results demonstrate that the SVM model, combined with automated smart crawling, achieves an 85% accuracy rate. © 2023 The Authors. Published by Elsevier B.V.

关键词： smart crawling Social media SVM Twitter weather

What is a Number, That a Large Language Model May Know It?

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Marjieh, Raja Veselovsky, Veniamin Griffiths, Thomas L. Sucholutsky, Ilia Department of Psychology Princeton University United States Department of Computer Science Princeton University United States Center for Data Science New York University United States

Numbers are a basic part of how humans represent and describe the world around them. As a consequence, learning effective representations of numbers is critical for the success of large language models as they become more integrated into everyday decisions. However, these models face a challenge: depending on context, the same sequence of digit tokens, e.g., 911, can be treated as a number or as a string. What kind of representations arise from this duality, and what are its downstream implications? Using a similarity-based prompting technique from cognitive science, we show that LLMs learn representational spaces that blend string-like and numerical representations. In particular, we show that elicited similarity judgments from these models over integer pairs can be captured by a combination of Levenshtein edit distance and numerical Log-Linear distance, suggesting an entangled representation. In a series of experiments we show how this entanglement is reflected in the latent embeddings, how it can be reduced but not entirely eliminated by context, and how it can propagate into a realistic decision scenario. These results shed light on a representational tension in transformer models that must learn what a number is from text input. © 2025, CC BY.

关键词：

Practical Equivariances via Relational Conditional Neural Processes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Daolang Haussmann, Manuel Remes, Ulpu John, S.T. Clarté, Grégoire Luck, Kevin Sebastian Kaski, Samuel Acerbi, Luigi Department of Computer Science Aalto University Finland Department of Mathematics and Statistics University of Helsinki Finland Department of Computer Science University of Helsinki Finland Aalto University Finland Department of Computer Science University of Manchester United Kingdom Department of Computer Science Vrije Universiteit Amsterdam Netherlands

Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as in spatio-temporal modeling, Bayesian Optimization and continuous control, inherently contain equivariances – for example to translation – which the model can exploit for maximal performance. However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions. In this work, we propose Relational Conditional Neural Processes (RCNPs), an effective approach to incorporate equivariances into any neural process model. Our proposed method extends the applicability and impact of equivariant neural processes to higher dimensions. We empirically demonstrate the competitive performance of RCNPs on a large array of tasks naturally containing equivariances. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Decentralized online learning in general-sum stackelberg games 24

学校读者我要写书评

暂无评论

Decentralized online learning in general-sum stackelberg gam...

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Yaolong Yu Haipeng Chen Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Data Science William & Mary Williamsburg Virginia

We study an online learning problem in generalsum Stackelberg games, where players act in a decentralized and strategic manner. We study two settings depending on the type of information for the follower: (1) the limited information setting where the follower only observes its own reward, and (2) the side information setting where the follower has extra side information about the leader's reward. We show that for the follower, myopically best responding to the leader's action is the best strategy for the limited information setting, but not necessarily so for the side information setting - the follower can manipulate the leader's reward signals with strategic actions, and hence induce the leader's strategy to converge to an equilibrium that is better off for itself. Based on these insights, we study decentralized online learning for both players in the two settings. Our main contribution is to derive last-iterate convergence and sample complexity results in both settings. Notably, we design a new manipulation strategy for the follower in the latter setting, and show that it has an intrinsic advantage against the best response strategy. Our theories are also supported by empirical results.

关键词：