Word embeddings learned from massive text collections have demonstrated significant levels of discriminative biases. However, debias on the Chinese language, one of the most spoken languages, has been less explored. Meanwhile, existing literature relies on manually created supplementary data, which is time- and energy-consuming. In this work, we propose the first Chinese Gender-neutral word Embedding model (CGE) based on Word2vec, which learns gender-neutral word embeddings without any labeled data. Concretely, CGE utilizes and emphasizes the rich feminine and masculine information contained in radicals, i. e., a kind of component in Chinese characters, during the training procedure. This consequently alleviates discriminative gender biases. Experimental results on public benchmark datasets show that our unsupervised method outperforms the state-of-the-art supervised debiased word embedding models without sacrificing the functionality of the embedding model.
Distance metric learning (DML) is to learn a representation space equipped with a metric, such that examples from the same class are closer than examples from different classes with respect to the metric.
Despite recent advancements in automated speech recognition (ASR) technologies, reports of unequal performance across speakers of different demographic groups abound.
Character Animation aims to generating character videos from still images through driving signals.
In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation.
Advances on cryo-electron imaging technologies have led to a rapidly increasing number of density maps.
However, it is difficult to restore the lost details in the dark area by relying only on the RGB domain.
With the fast-growing and evolving omics data, the demand for streamlined and adaptable tools to handle the analysis continues to grow.
In this study, our goal is to identify general trends in the field and pinpoint high-impact research topics by analyzing a large dataset of mental health research papers.
Multi-modal fusion is increasingly being used for autonomous driving tasks, as images from different modalities provide unique information for feature extraction.
Current object detection models have achieved good results on many benchmark datasets, detecting objects in dark conditions remains a large challenge.
Medical artificial general intelligence (AGI) is an emerging field that aims to develop systems specifically designed for medical applications that possess the ability to understand, learn, and apply knowledge across a wide range of tasks and domains.
no code implementations • 15 Jun 2023 • Shubo Tian, Qiao Jin, Lana Yeganova, Po-Ting Lai, Qingqing Zhu, Xiuying Chen, Yifan Yang, Qingyu Chen, Won Kim, Donald C. Comeau, Rezarta Islamaj, Aadit Kapoor, Xin Gao, Zhiyong Lu
In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health.
The other factor is in the latent space, where the attacked inputs bring more variations to the hidden states.
In fully automatic mode, the presence of inevitable poor prompts (such as points outside the mask or boxes significantly larger than the mask) can significantly mislead mask generation.
To address these two challenges, we first propose a unified topic encoder, which jointly discovers latent topics from the document and various kinds of side information.
To quantify the correlation in multi-modal information, we model the uncertainty, as the inverse of data information, in different modalities and embed it in the bounding box generation.
Skin and subcutaneous diseases rank high among the leading contributors to the global burden of nonfatal diseases, impacting a considerable portion of the population.
no code implementations • 7 Apr 2023 • Gongning Luo, Kuanquan Wang, Jun Liu, Shuo Li, Xinjie Liang, Xiangyu Li, Shaowei Gan, Wei Wang, Suyu Dong, Wenyi Wang, Pengxin Yu, Enyou Liu, Hongrong Wei, Na Wang, Jia Guo, Huiqi Li, Zhao Zhang, Ziwei Zhao, Na Gao, Nan An, Ashkan Pakzad, Bojidar Rangelov, Jiaqi Dou, Song Tian, Zeyu Liu, Yi Wang, Ampatishan Sivalingam, Kumaradevan Punithakumar, Zhaowen Qiu, Xin Gao
Efficient automatic segmentation of multi-level (i. e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications.
The SGPT-RL method achieved better results than Reinvent on the ACE2 task, where molecular docking was used as the optimization goal.
As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples.
Revoking personal private data is one of the basic human rights, which has already been sheltered by several privacy-preserving laws in many countries.
However, there are few open-source frameworks for federated heterogeneous medical image analysis with personalization and privacy protection simultaneously without the demand to modify the existing model structures or to share any private data.
While previous methods reported fair performance, their models usually do not take advantage of multi-modal data and they are unable to handle new drugs or cell lines.
This is particularly evident for the learning-based multi-target landmark detection, where algorithms could be misleading to learn primarily the variation of background due to the varying FOV, failing the detection of targets.
Nowadays, time-stamped web documents related to a general news query floods spread throughout the Internet, and timeline summarization targets concisely summarizing the evolution trajectory of events along the timeline.
Our work targets at searching feasible adversarial perturbation to attack a classifier with high-dimensional categorical inputs in a domain-agnostic setting.
Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns.
We first propose a Multi-granularity Unsupervised Summarization model (MUS) as a simple and low-cost solution to the task.
In our work, we propose to learn features in medical images by training ConvNets to recognize the geometric transformation applied to images and present a simple self-supervised task that can easily predict the geometric transformation.
The evaluation of factual consistency also shows that our model generates more faithful summaries than baselines.
In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i. e., the point cloud videos.
One of the main challenges for feature representation in deep learning-based classification is the design of appropriate loss functions that exhibit strong discriminative power.
We verify the effectiveness of PAL on class-imbalanced learning and noise-tolerant learning by extensive experiments on synthetic and real-world datasets.
The related work section is an important component of a scientific paper, which highlights the contribution of the target paper in the context of the reference papers.
Skeleton extraction is a task focused on providing a simple representation of an object by extracting the skeleton from the given binary or RGB image.
The rapid growth in the number of experimental and predicted protein structures and more complicated protein structures challenge users in computational biology for utilizing the structural information and protein surface property representation.
By introducing the maximum viral load and recovery time after viral infection, we quantitatively studied the protective effect of vaccines against viral infection.
The development of online economics arouses the demand of generating images of models on product clothes, to display new clothes and promote sales.
Ranked #2 on Virtual Try-on on MPV
To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks.
Existing 2D image-based virtual try-on methods aim to transfer a target clothing image onto a reference person, which has two main disadvantages: cannot control the size and length precisely; unable to accurately estimate the user's figure in the case of users wearing thick clothes, resulting in inaccurate dressing effect.
In this paper, motivated by the residual learning and global aggregation, we propose a simple yet general and effective knowledge distillation framework called double similarity distillation (DSD) to improve the classification accuracy of all existing compact networks by capturing the similarity knowledge in pixel and category dimensions, respectively.
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images.
Ranked #1 on Object Detection on Waymo Open Dataset
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images.
We aim to establish an individual metabolic connectome method to characterize the aberrant connectivity patterns and topological alterations of the individual-level brain metabolic connectome and their diagnostic value in PD.
In addition, we propose a novel multi-head collaborative training scheme to improve the performance, which is collaboratively supervised by multiple heads with the same structure but different parameters.
1 code implementation • • Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Haoying Zhang, Xiaodan Liang, Teruko Mitamura, Eric P. Xing, Zhiting Hu
Empirical natural language processing (NLP) systems in application domains (e. g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis, generation, and visualization.
In this paper, we introduce the One-sample Guided Object Representation Disassembling (One-GORD) method, which only requires one annotated sample for each object category to learn disassembled object representation from unannotated images.
We use two wide-area aerial videos to compare the performance of five object detection algorithms in the absence and in the presence of our post-processing scheme.
In this paper, we formulate such a task offloading problem with unknown system dynamics as a combinatorial multi-armed bandit (CMAB) problem with long-term constraints on time-averaged energy consumptions.
Due to uncertainties in practice such as unknown file popularities, cache placement scheme design is still an open problem with unresolved challenges: 1) how to maintain time-averaged storage costs under budgets, 2) how to incorporate online learning to aid cache placement to minimize performance loss (a. k. a.
Networking and Internet Architecture Signal Processing
In this paper, we formulate the problem of service chain composition in NFV systems with failures as a non-cooperative game.
2 code implementations • 18 Jun 2020 • Qiang Yang, Hind Alamro, Somayah Albaradei, Adil Salhi, Xiaoting Lv, Changsheng Ma, Manal Alshehri, Inji Jaber, Faroug Tifratene, Wei Wang, Takashi Gojobori, Carlos M. Duarte, Xin Gao, Xiangliang Zhang
Since the first alert launched by the World Health Organization (5 January, 2020), COVID-19 has been spreading out to over 180 countries and territories.
Similar to algorithms, the optimal depth of a deep architecture may be different for different input instances, either to avoid ``over-thinking'', or because we want to compute less for operations converged already.
The COVID-19 crisis called for rapid reaction from all the fields of biomedical research.
In this paper, we study a new representation-learning task, which we termed as disassembling object representations.
The key idea of E2Efold is to directly predict the RNA base-pairing matrix, and use an unrolled algorithm for constrained programming as the template for deep architectures to enforce constraints.
A major bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) algorithm for large-scale Federated Learning is the communication overhead on pushing local gradients and pulling global model.
It also models the correlation between clinical features to enhance the ones which strongly indicate the health status and thus can maintain a state-of-the-art performance in terms of prediction accuracy while providing qualitative interpretability.
Predicting the patient's clinical outcome from the historical electronic medical records (EMR) is a fundamental research problem in medical informatics.
The performance of object instance segmentation in remote sensing images has been greatly improved through the introduction of many landmark frameworks based on convolutional neural network.
Deep learning, which is especially formidable in handling big data, has achieved great success in various fields, including bioinformatics.
no code implementations • 31 Oct 2018 • Keyang Xu, Mike Lam, Jingzhi Pang, Xin Gao, Charlotte Band, Piyush Mathur, Frank Papay, Ashish K. Khanna, Jacek B. Cywinski, Kamal Maheshwari, Pengtao Xie, Eric Xing
This study presents a multimodal machine learning model to predict ICD-10 diagnostic codes.
In this work we further develop our deep learning approach that was relatively successful to discriminate short promoter and non-promoter sequences.
This paper puts forward a broad-spectrum improvement for reinforcement learning algorithms, which combines the policies using original rewards and inverse (negative) rewards.
We demonstrate, both theoretically and empirically, that the last weight layer of a neural network converges to a linear SVM trained on the output of the last hidden layer, for both the binary case and the multi-class case with the commonly used cross-entropy loss.
A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting.
Our method combines the strength of deep learning and statistical inference, where deep learning captures the underlying distribution of the fluorophores that are consistent with the observed time-series fluorescent images by exploring local features and correlation along time-axis, and statistical inference further refines the ultrastructure extracted by deep learning and endues physical meaning to the final image.
Second, we evaluate our method on predicting gene-disease associations based on phenotype similarity by generating vector representations of genes and diseases using a phenotype ontology, and applying the obtained vectors to predict gene-disease associations.
We propose the Onto2Vec method, an approach to learn feature vectors for biological entities based on their annotations to biomedical ontologies.
Predicting discharge medications right after a patient being admitted is an important clinical decision, which provides physicians with guidance on what type of medication regimen to plan for and what possible changes on initial medication may occur during an inpatient stay.
Multi-Task Learning (MTL) can enhance a classifier's generalization performance by learning multiple related tasks simultaneously.
To solve this problem, we propose to learn the class label predictors by maximizing the correntropy between the predicted labels and the true labels of the training samples, under the regularized Maximum Correntropy Criteria (MCC) framework.
Recently, manifold regularized NMF used a nearest neighbor graph to regulate the learning of factorization parameter matrices and has shown its advantage over traditional NMF methods for data representation problems.
In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label.
To solve these bottlenecks, we propose two novel graph-regularized NMF methods, AGNMFFS and AGNMFMK, by introducing feature selection and multiple-kernel learning to the graph regularized NMF, respectively.
In this paper, we try to answer these questions by developing the first joint sparse coding and ranking score learning algorithm.
In this paper, we propose a novel image set representation and classification method by maximizing the margin of image sets.
However, the existing graph regularized ranking methods are very sensitive to the choice of the graph model and parameters, and this remains a difficult problem for most of the protein domain ranking methods.