首页/论文/1808.04456

arXiv 1808.044562018-08cs.LGcs.AIcs.CVstat.ML

Multimodal Deep Neural Networks using Both Engineered and Learned Representations for Biodegradability Prediction

Pacific Northwest National Lab (PNNL)（西北太平洋国家实验室）；University of Washington (UW)（华盛顿大学）

Garrett B. Goh, Khushmeen Sakloth, Charles Siegel, Abhinav Vishnu, Jim Pfaendtner

备注：: Submitted to a peer-reviewed ML conference

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Deep learning algorithms excel at extracting patterns from raw data, and with large datasets, they have been very successful in computer vision and natural language applications. However, in other domains, large datasets on which to learn representations from may not exist. In this work, we develop a novel multimodal CNN-MLP neural network architecture that utilizes both domain-specific feature engineering as well as learned representations from raw data. We illustrate the effectiveness of such network designs in the chemical sciences, for predicting biodegradability. DeepBioD, a multimodal CNN-MLP network is more accurate than either standalone network designs, and achieves an error classification rate of 0.125 that is 27% lower than the current state-of-the-art. Thus, our work indicates that combining traditional feature engineering with representation learning can be effective, particularly in situations where labeled data is limited.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

超越化学语言：一种增强分子性质预测的多模态方法

Beyond Chemical Language: A Multimodal Approach to Enhance Molecular Property Prediction

IBM Research Brazil（IBM巴西研究院）；IBM Research Almaden（IBM阿尔马登研究院）

本文提出多模态模型MULTIMODAL-MOLFORMER，通过因果多阶段特征选择将Mordred物理化学特征与MOLFORMER分子嵌入相融合，在生物降解性和PFAS毒性预测等任务上优于现有最先进算法，并有效降低了特征维度。

2023-06-22cs.LGphysics.chem-phq-bio.QM

金融应用中多模态事件序列的基础模型

A Foundation Model for Multimodal Event Sequences in Financial Applications

Sber（俄罗斯储蓄银行）；Sber AI Lab（俄罗斯储蓄银行人工智能实验室）

研究金融应用中多模态事件序列预测建模，提出预训练基础变压器模型统一多源事件成序列，经下一个事件预测学习通用表示，结合现有特征训练轻量级神经模型用于多下游任务，优于传统模型并减少开发开销且已应用取得业务改进。

2026-07-14cs.AIcs.LG

Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis

University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Curai（Curai公司）

Multimodal language analysis often considers relationships between features based on text and those based on acoustical and visual properties. Text features typically outperform non-text features in sentiment analysis or emotion recognition tasks in part because the text features are derived from advanced language models or word embeddings trained on massive data sources while audio and video features are human-engineered and comparatively underdeveloped. Given that the text, audio, and video are describing the same utterance in different ways, we hypothesize that the multimodal sentiment anal…

2019-11-30cs.LGstat.ML

A Framework for Learning Invariant Physical Relations in Multimodal Sensory Processing

Technische Hochschule Ingolstadt（因戈尔施塔特应用技术大学）；Merck KGaA（默克集团）；Audi Konfuzius-Institut Ingolstadt（奥迪英戈尔施塔特孔子学院）

Perceptual learning enables humans to recognize and represent stimuli invariant to various transformations and build a consistent representation of the self and physical world. Such representations preserve the invariant physical relations among the multiple perceived sensory cues. This work is an attempt to exploit these principles in an engineered system. We design a novel neural network architecture capable of learning, in an unsupervised manner, relations among multiple sensory cues. The system combines computational principles, such as competition, cooperation, and correlation, in a neura…

2020-06-30cs.CVcs.LGcs.NE

用于无触发语音助手的高效多模态神经网络

Efficient Multimodal Neural Networks for Trigger-less Voice Assistants

Apple（苹果公司）

提出一种基于神经网络的音频-手势多模态融合系统，用于无触发语音助手，解决了现有启发式方法适应性差、可扩展性有限及存在人类偏见的问题，实现了精准调用、广泛泛化、低功耗设备部署及开发效率提升。

2023-05-20cs.HCcs.LG

Conditional Generative Modeling via Learning the Latent Space

Australian National University（澳大利亚国立大学）；CSIRO, Data61（澳大利亚联邦科学与工业研究组织数据61中心）；University of Moratuwa（莫拉图瓦大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework for conditional generation in multimodal spaces, that uses latent variables to model generalizable learning patterns while minimizing a family of regression cost functions. At inference, the latent variables are optimized to find optimal solutions corresponding to multiple output modes. Compared to existing generative solutions, in multimodal spaces, our appro…

2020-10-09cs.CVcs.LG

更多相关论文收起更多论文

通过多模态机器学习改进治疗性抗体重构

Improved Therapeutic Antibody Reformatting through Multimodal Machine Learning

University of Pennsylvania（宾夕法尼亚大学）；BigHat Biosciences（BigHat生物技术公司）

针对抗体重构的工程挑战，提出结合序列与结构的多模态机器学习框架预测重构成功，在真实数据集上优于大型预训练语言模型，尤其在新抗体无数据场景下实现高准确率，助力候选优先排序。

2025-09-23cs.LG

基于核双样本检验的多模态多用户表面识别

Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Test

Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Stuttgart（斯图加特大学）；RWTH Aachen University（亚琛工业大学）

本文提出基于核双样本检验的数据对数据框架，直接处理图像、声音和触觉等多模态异构数据，在108类表面识别任务中达到97.2%准确率，并超越最先进算法6%。

2023-03-08cs.CVcs.LGcs.RO

一种用于人形机器人运动的融合激光雷达和深度数据的鲁棒高度图生成的混合自编码器

A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion

Institute of Mechatronic Systems, Leibniz University Hannover（机械系统研究所，莱比锡洪堡大学）

本文提出了一种混合自编码器，通过融合激光雷达和深度数据生成鲁棒的高度图，以提升人形机器人在非结构化环境中的运动性能。

2026-02-05cs.LGcs.RO

Mode matching in GANs through latent space learning and inversion

Indian Institute of Technology Delhi（德里印度理工学院）

Generative adversarial networks (GANs) have shown remarkable success in generation of unstructured data, such as, natural images. However, discovery and separation of modes in the generated space, essential for several tasks beyond naive data generation, is still a challenge. In this paper, we address the problem of imposing desired modal properties on the generated space using a latent distribution, engineered in accordance with the modal properties of the true data distribution. This is achieved by training a latent space inversion network in tandem with the generative network using a diverg…

2019-03-24cs.CVcs.LG

The Many Faces of Link Fraud

Carnegie Mellon University（卡内基梅隆大学）；Google Research（谷歌研究院）

Most past work on social network link fraud detection tries to separate genuine users from fraudsters, implicitly assuming that there is only one type of fraudulent behavior. But is this assumption true? And, in either case, what are the characteristics of such fraudulent behaviors? In this work, we set up honeypots ("dummy" social network accounts), and buy fake followers (after careful IRB approval). We report the signs of such behaviors including oddities in local network connectivity, account attributes, and similarities and differences across fraud providers. Most valuably, we discover an…

2017-09-11cs.LGcs.SI

通过大语言模型进行语义特征工程提升肺癌治疗预后预测

Enhancing Lung Cancer Treatment Outcome Prediction through Semantic Feature Engineering Using Large Language Models

Mayo Clinic（妙佑医疗国际）

本研究利用大语言模型进行语义特征工程，提升肺癌治疗预后预测的准确性与可解释性。

2025-12-01cs.AIcs.LG

Single-modal and Multi-modal False Arrhythmia Alarm Reduction using Attention-based Convolutional and Recurrent Neural Networks

Northern Arizona University（北亚利桑那大学）

This study proposes a deep learning model that effectively suppresses the false alarms in the intensive care units (ICUs) without ignoring the true alarms using single- and multimodal biosignals. Most of the current work in the literature are either rule-based methods, requiring prior knowledge of arrhythmia analysis to build rules, or classical machine learning approaches, depending on hand-engineered features. In this work, we apply convolutional neural networks to automatically extract time-invariant features, an attention mechanism to put more emphasis on the important regions of the input…

2019-09-25cs.LGeess.SPq-bio.QM

一种用于材料断裂预测的基础模型

A Foundation Model for Material Fracture Prediction

Energy and Natural Resources Security Group, EES-16, Earth and Environmental Sciences Division, Los Alamos National Laboratory（能源与自然资源安全组，EES-16，地球与环境科学部，洛斯阿拉莫斯国家实验室）；National Security Earth Science Group, EES-17, Earth and Environmental Sciences Division, Los Alamos National Laboratory（国家安全地球科学组，EES-17，地球与环境科学部，洛斯阿拉莫斯国家实验室）；Materials and Physical Data Group, XCP-5, X Computational Physics Division, Los Alamos National Laboratory（材料与物理数据组，XCP-5，X计算物理部，洛斯阿拉莫斯国家实验室）；High Performance Computing Design Group, HPC-DES, High Performance Computing Division, Los Alamos National Laboratory（高性能计算设计组，HPC-DES，高性能计算部，洛斯阿拉莫斯国家实验室）；Statistical Sciences Group, CCS-6, Computer, Computational and Statistical Sciences Division, Los Alamos National Laboratory（统计科学组，CCS-6，计算机、计算与统计科学部，洛斯阿拉莫斯国家实验室）

针对现有材料断裂预测方法泛化性差或计算成本高的问题，提出基于Transformer的多模态基础模型，可跨多类材料与载荷条件预测断裂，仅需少量数据即可微调并泛化到新材，为断裂预测提供统一可扩展方案。

2025-07-30cond-mat.mtrl-scics.LGphysics.geo-ph