Advances in neural information processing systems最新文献_第8页

Learning Concept Credible Models for Mitigating Shortcuts. 减少捷径的学习概念可信模型。

Advances in neural information processing systems Pub Date : 2022-12-01

Jiaxuan Wang, Sarah Jabbour, Maggie Makar, Michael Sjoding, Jenna Wiens

引用次数: 0

Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers. 看到森林和树木:用变压器建立个人和集体动态的表示。

Advances in neural information processing systems Pub Date : 2022-12-01

Ran Liu, Mehdi Azabou, Max Dabagia, Jingyun Xiao, Eva L Dyer

{"title":"Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers.","authors":"Ran Liu, Mehdi Azabou, Max Dabagia, Jingyun Xiao, Eva L Dyer","doi":"","DOIUrl":"","url":null,"abstract":"Complex time-varying systems are often studied by abstracting away from the dynamics of individual components to build a model of the population-level dynamics from the start. However, when building a population-level description, it can be easy to lose sight of each individual and how they contribute to the larger picture. In this paper, we present a novel transformer architecture for learning from time-varying data that builds descriptions of both the individual as well as the collective population dynamics. Rather than combining all of our data into our model at the onset, we develop a separable architecture that operates on individual time-series first before passing them forward; this induces a permutation-invariance property and can be used to transfer across systems of different size and order. After demonstrating that our model can be applied to successfully recover complex interactions and dynamics in many-body systems, we apply our approach to populations of neurons in the nervous system. On neural activity datasets, we show that our model not only yields robust decoding performance, but also provides impressive performance in transfer across recordings of different animals without any neuron-level correspondence. By enabling flexible pre-training that can be transferred to neural recordings of different size and order, our work provides a first step towards creating a foundation model for neural decoding.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"2377-2391"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10260251/pdf/nihms-1848966.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9623586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Benchmark for Compositional Visual Reasoning. 组合式视觉推理的基准。

Advances in neural information processing systems Pub Date : 2022-12-01

Aimen Zerroug, Mohit Vaishnav, Julien Colin, Sebastian Musslick, Thomas Serre

{"title":"A Benchmark for Compositional Visual Reasoning.","authors":"Aimen Zerroug, Mohit Vaishnav, Julien Colin, Sebastian Musslick, Thomas Serre","doi":"","DOIUrl":"","url":null,"abstract":"A fundamental component of human vision is our ability to parse complex visual scenes and judge the relations between their constituent objects. AI benchmarks for visual reasoning have driven rapid progress in recent years with state-of-the-art systems now reaching human accuracy on some of these benchmarks. Yet, there remains a major gap between humans and AI systems in terms of the sample efficiency with which they learn new visual reasoning tasks. Humans' remarkable efficiency at learning has been at least partially attributed to their ability to harness compositionality - allowing them to efficiently take advantage of previously gained knowledge when learning new tasks. Here, we introduce a novel visual reasoning benchmark, Compositional Visual Relations (CVR), to drive progress towards the development of more data-efficient learning algorithms. We take inspiration from fluid intelligence and non-verbal reasoning tests and describe a novel method for creating compositions of abstract rules and generating image datasets corresponding to these rules at scale. Our proposed benchmark includes measures of sample efficiency, generalization, compositionality, and transfer across task rules. We systematically evaluate modern neural architectures and find that convolutional architectures surpass transformer-based architectures across all performance measures in most data regimes. However, all computational models are much less data efficient than humans, even after learning informative visual representations using self-supervision. Overall, we hope our challenge will spur interest in developing neural architectures that can learn to harness compositionality for more efficient learning.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 DB","pages":"29776-29788"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10396074/pdf/nihms-1856061.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9948508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling. 通过高效的协作开源采样，不上传数据的外包培训。

Advances in neural information processing systems Pub Date : 2022-12-01

Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger

{"title":"Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling.","authors":"Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger","doi":"","DOIUrl":"","url":null,"abstract":"As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device. Traditional outsourcing requires uploading device data to the cloud server, which can be infeasible in many real-world applications due to the often sensitive nature of the collected data and the limited communication bandwidth. To tackle these challenges, we propose to leverage widely available open-source data, which is a massive dataset collected from public and heterogeneous sources (e.g., Internet images). We develop a novel strategy called Efficient Collaborative Open-source Sampling (ECOS) to construct a proximal proxy dataset from open-source data for cloud training, in lieu of client data. ECOS probes open-source data on the cloud server to sense the distribution of client data via a communication- and computation-efficient sampling process, which only communicates a few compressed public features and client scalar responses. Extensive empirical studies show that the proposed ECOS improves the quality of automated client labeling, model compression, and label outsourcing when applied in various learning scenarios.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"20133-20146"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10157828/pdf/nihms-1888095.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9439660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Manifold Interpolating Optimal-Transport Flows for Trajectory Inference. 轨迹推断的流形插值最优输运流。

Advances in neural information processing systems Pub Date : 2022-12-01

Guillaume Huguet, D S Magruder, Alexander Tong, Oluwadamilola Fasina, Manik Kuchroo, Guy Wolf, Smita Krishnaswamy

{"title":"Manifold Interpolating Optimal-Transport Flows for Trajectory Inference.","authors":"Guillaume Huguet, D S Magruder, Alexander Tong, Oluwadamilola Fasina, Manik Kuchroo, Guy Wolf, Smita Krishnaswamy","doi":"","DOIUrl":"","url":null,"abstract":"We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) that learns stochastic, continuous population dynamics from static snapshot samples taken at sporadic timepoints. MIOFlow combines dynamic models, manifold learning, and optimal transport by training neural ordinary differential equations (Neural ODE) to interpolate between static population snapshots as penalized by optimal transport with manifold ground distance. Further, we ensure that the flow follows the geometry by operating in the latent space of an autoencoder that we call a geodesic autoencoder (GAE). In GAE the latent space distance between points is regularized to match a novel multiscale geodesic distance on the data manifold that we define. We show that this method is superior to normalizing flows, Schrödinger bridges and other generative models that are designed to flow from noise to data in terms of interpolating between populations. Theoretically, we link these trajectories with dynamic optimal transport. We evaluate our method on simulated data with bifurcations and merges, as well as scRNA-seq data from embryoid body differentiation, and acute myeloid leukemia treatment.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"29705-29718"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10312391/pdf/nihms-1883152.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9806927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bivariate Causal Discovery for Categorical Data via Classification with Optimal Label Permutation. 基于最优标签排列分类的分类数据双变量因果发现。

Advances in neural information processing systems Pub Date : 2022-12-01

Yang Ni

引用次数: 0

OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology. openrh:利用术中刺激拉曼组织学优化脑肿瘤手术。

Advances in neural information processing systems Pub Date : 2022-12-01

Cheng Jiang, Asadur Chowdury, Xinhai Hou, Akhil Kondepudi, Christian W Freudiger, Kyle Conway, Sandra Camelo-Piragua, Daniel A Orringer, Honglak Lee, Todd C Hollon

{"title":"OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology.","authors":"Cheng Jiang, Asadur Chowdury, Xinhai Hou, Akhil Kondepudi, Christian W Freudiger, Kyle Conway, Sandra Camelo-Piragua, Daniel A Orringer, Honglak Lee, Todd C Hollon","doi":"","DOIUrl":"","url":null,"abstract":"Accurate intraoperative diagnosis is essential for providing safe and effective care during brain tumor surgery. Our standard-of-care diagnostic methods are time, resource, and labor intensive, which restricts access to optimal surgical treatments. To address these limitations, we propose an alternative workflow that combines stimulated Raman histology (SRH), a rapid optical imaging method, with deep learning-based automated interpretation of SRH images for intraoperative brain tumor diagnosis and real-time surgical decision support. Here, we present OpenSRH, the first public dataset of clinical SRH images from 300+ brain tumors patients and 1300+ unique whole slide optical images. OpenSRH contains data from the most common brain tumors diagnoses, full pathologic annotations, whole slide tumor segmentations, raw and processed optical imaging data for end-to-end model development and validation. We provide a framework for patch-based whole slide SRH classification and inference using weak (i.e. patient-level) diagnostic labels. Finally, we benchmark two computer vision tasks: multiclass histologic brain tumor classification and patch-based contrastive representation learning. We hope OpenSRH will facilitate the clinical translation of rapid optical imaging and real-time ML-based surgical decision support in order to improve the access, safety, and efficacy of cancer surgery in the era of precision medicine. Dataset access, code, and benchmarks are available at https://opensrh.mlins.org.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 DB","pages":"28502-28516"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10114931/pdf/nihms-1873939.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9442704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient coding, channel capacity, and the emergence of retinal mosaics. 有效的编码，通道容量，和视网膜马赛克的出现。

Advances in neural information processing systems Pub Date : 2022-12-01

Na Young Jun, Greg D Field, John M Pearson

{"title":"Efficient coding, channel capacity, and the emergence of retinal mosaics.","authors":"Na Young Jun, Greg D Field, John M Pearson","doi":"","DOIUrl":"","url":null,"abstract":"Among the most striking features of retinal organization is the grouping of its output neurons, the retinal ganglion cells (RGCs), into a diversity of functional types. Each of these types exhibits a mosaic-like organization of receptive fields (RFs) that tiles the retina and visual space. Previous work has shown that many features of RGC organization, including the existence of ON and OFF cell types, the structure of spatial RFs, and their relative arrangement, can be predicted on the basis of efficient coding theory. This theory posits that the nervous system is organized to maximize information in its encoding of stimuli while minimizing metabolic costs. Here, we use efficient coding theory to present a comprehensive account of mosaic organization in the case of natural videos as the retinal channel capacity-the number of simulated RGCs available for encoding-is varied. We show that mosaic density increases with channel capacity up to a series of critical points at which, surprisingly, new cell types emerge. Each successive cell type focuses on increasingly high temporal frequencies and integrates signals over larger spatial areas. In addition, we show theoretically and in simulation that a transition from mosaic alignment to anti-alignment across pairs of cell types is observed with increasing output noise and decreasing input noise. Together, these results offer a unified perspective on the relationship between retinal mosaics, efficient coding, and channel capacity that can help to explain the stunning functional diversity of retinal cell types.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"32311-32324"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10168625/pdf/nihms-1894361.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9522115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

StrokeRehab: A Benchmark Dataset for Sub-second Action Identification. 中风康复：亚秒动作识别的基准数据集。

Advances in neural information processing systems Pub Date : 2022-12-01

Aakash Kaku, Kangning Liu, Avinash Parnandi, Haresh Rengaraj Rajamohan, Kannan Venkataramanan, Anita Venkatesan, Audre Wirtanen, Natasha Pandit, Heidi Schambra, Carlos Fernandez-Granda

{"title":"StrokeRehab: A Benchmark Dataset for Sub-second Action Identification.","authors":"Aakash Kaku, Kangning Liu, Avinash Parnandi, Haresh Rengaraj Rajamohan, Kannan Venkataramanan, Anita Venkatesan, Audre Wirtanen, Natasha Pandit, Heidi Schambra, Carlos Fernandez-Granda","doi":"","DOIUrl":"","url":null,"abstract":"Automatic action identification from video and kinematic data is an important machine learning problem with applications ranging from robotics to smart health. Most existing works focus on identifying coarse actions such as running, climbing, or cutting vegetables, which have relatively long durations and a complex series of motions. This is an important limitation for applications that require identification of more elemental motions at high temporal resolution. For example, in the rehabilitation of arm impairment after stroke, quantifying the training dose (number of repetitions) requires differentiating motions with sub-second durations. Our goal is to bridge this gap. To this end, we introduce a large-scale, multimodal dataset, StrokeRehab, as a new action-recognition benchmark that includes elemental short-duration actions labeled at a high temporal resolution. StrokeRehab consists of high-quality inertial measurement unit sensor and video data of 51 stroke-impaired patients and 20 healthy subjects performing activities of daily living like feeding, brushing teeth, etc. Because it contains data from both healthy and impaired individuals, StrokeRehab can be used to study the influence of distribution shift in action-recognition tasks. When evaluated on StrokeRehab, current state-of-the-art models for action segmentation produce noisy predictions, which reduces their accuracy in identifying the corresponding sequence of actions. To address this, we propose a novel approach for high-resolution action identification, inspired by speech-recognition techniques, which is based on a sequence-to-sequence model that directly predicts the sequence of actions. This approach outperforms current state-of-the-art methods on StrokeRehab, as well as on the standard benchmark datasets 50Salads, Breakfast, and Jigsaws.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"1671-1684"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10530637/pdf/nihms-1931424.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41179579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. 诱捕和替换:通过将后门攻击诱捕到易于替换的子网来防御后门攻击。

Advances in neural information processing systems Pub Date : 2022-12-01

Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang

{"title":"Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork.","authors":"Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang","doi":"","DOIUrl":"","url":null,"abstract":"Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor samples. In this paper, we propose a brand-new backdoor defense strategy, which makes it much easier to remove the harmful influence of backdoor samples from the model. Our defense strategy, Trap and Replace, consists of two stages. In the first stage, we bait and trap the backdoors in a small and easy-to-replace subnetwork. Specifically, we add an auxiliary image reconstruction head on top of the stem network shared with a light-weighted classification head. The intuition is that the auxiliary image reconstruction task encourages the stem network to keep sufficient low-level visual features that are hard to learn but semantically correct, instead of overfitting to the easy-to-learn but semantically incorrect backdoor correlations. As a result, when trained on backdoored datasets, the backdoors are easily baited towards the unprotected classification head, since it is much more vulnerable than the shared stem, leaving the stem network hardly poisoned. In the second stage, we replace the poisoned light-weighted classification head with an untainted one, by re-training it from scratch only on a small holdout dataset with clean samples, while fixing the stem network. As a result, both the stem and the classification head in the final network are hardly affected by backdoor training samples. We evaluate our method against ten different backdoor attacks. Our method outperforms previous state-of-the-art methods by up to 20.57%, 9.80%, and 13.72% attack success rate and on-average 3.14%, 1.80%, and 1.21% clean classification accuracy on CIFAR10, GTSRB, and ImageNet-12, respectively. Code is available at https://github.com/VITA-Group/Trap-and-Replace-Backdoor-Defense.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"35 ","pages":"36026-36039"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10115557/pdf/nihms-1888093.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9378703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0