We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

/pdf/you-only-look-once-unified-real-time-object-detection-3gan6roe1o.pdf

You Only Look Once: Unified, Real-Time Object Detection

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by C1-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.

/pdf/robust-face-recognition-via-sparse-representation-4bfqv6y74o.pdf

Robust Face Recognition via Sparse Representation

Computational single-cell RNA-seq (scRNA-seq) methods have been successfully applied to experiments representing a single condition, technology, or species to discover and define cellular phenotypes. However, identifying subpopulations of cells that are present across multiple data sets remains challenging. Here, we introduce an analytical strategy for integrating scRNA-seq data sets based on common sources of variation, enabling the identification of shared populations across data sets and downstream comparative analysis. We apply this approach, implemented in our R toolkit Seurat (http://satijalab.org/seurat/), to align scRNA-seq data sets of peripheral blood mononuclear cells under resting and stimulated conditions, hematopoietic progenitors sequenced using two profiling technologies, and pancreatic cell 'atlases' generated from human and mouse islets. In each case, we learn distinct or transitional cell states jointly across data sets, while boosting statistical power through integrated analysis. Our approach facilitates general comparisons of scRNA-seq data sets, potentially deepening our understanding of how distinct cell states respond to perturbation, disease, and evolution.

/pdf/integrating-single-cell-transcriptomic-data-across-different-3dtsi5w7ob.pdf

Integrating single-cell transcriptomic data across different conditions, technologies, and species.

Graph neural networks (GNNs) mainly rely on the message-passing paradigm to propagate node features and build interactions, and different graph learning tasks require different ranges of node interactions. In this work, we explore the capacity of GNNs to capture interactions between nodes under contexts with different complexities. We discover that GNNs are usually unable to capture the most informative kinds of interaction styles for diverse graph learning tasks , and thus name this phenomenon as GNNs’ representation bottleneck. As a response, we demonstrate that the inductive bias introduced by existing graph construction mechanisms can prevent GNNs from learning interactions of the most appropriate complexity, i.e. , resulting in the representation bottleneck. To ad-dress that limitation, we propose a novel graph rewiring approach based on interaction patterns learned by GNNs to adjust the receptive ﬁelds of each node dynamically. Extensive experiments on both real-world and synthetic datasets prove the effectiveness of our algorithm to alleviate the representation bottleneck and its superiority to enhance the performance of GNNs over state-of-the-art graph rewiring baselines.

Discovering and Explaining the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions

The secondary structure of ribonucleic acid (RNA) is more stable and accessible in the cell than its tertiary structure, making it essential for functional prediction. Although deep learning has shown promising results in this field, current methods suffer from poor generalization and high complexity. In this work, we present RFold, a simple yet effective RNA secondary structure prediction in an end-to-end manner. RFold introduces a decoupled optimization process that decomposes the vanilla constraint satisfaction problem into row-wise and column-wise optimization, simplifying the solving process while guaranteeing the validity of the output. Moreover, RFold adopts attention maps as informative representations instead of designing hand-crafted features. Extensive experiments demonstrate that RFold achieves competitive performance and about eight times faster inference efficiency than the state-of-the-art method. The code and Colab demo are available in \href{http://github.com/A4Bio/RFold}{http://github.com/A4Bio/RFold}.

RFold: RNA Secondary Structure Prediction with Decoupled Optimization


Precipitation is a vital process in water cycle. Accurate estimation of the precipitation rate underpins the success of hydrological simulations, flood predictions, and water resource management. Satellite infrared (IR) data, with high temporal resolution and wide coverages, have been commonly used in precipitation inversion. However, existing IR-based precipitation retrieval algorithms suffer from various problems such as overestimation in dry regions, poor performance in extreme rainfall events, and reliance on an empirical cloud-top brightness-rain rate relationship. To resolve these problems, we construct a deep learning model using a spherical convolutional neural network to properly represent the Earth’s spherical surface. With data inputted directly from IR band 3, 4, and 6 of the operational Geostationary Operational Environmental Satellite (GOES), our new model of Precipitation Estimation based on IR data with Spherical Convolutional Neural Network (PEISCNN) was first trained and tested with a three-month-long dataset, and then validated in a two-year period. Compared to the commonly used IR-based precipitation product PERSIANN CCS (the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Network, Cloud Classification System), PEISCNN showed significant improvement in the metrics of POD, CSI, RMSE and CC, especially in the dry region and for extreme rainfall events. Decomposed with the 4CED method, the overestimation of PEISCNN was averaged 47.66% lower than the CCS at the hourly scale. The PEISCNN model may provide a promising way to produce an improved IR-based precipitation product to benefit a wide range of hydrological applications.

Precipitation estimation based on infrared data with a spherical convolutional neural network

Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding. Most existing neural network approaches learn latent representations by minimizing reconstruction errors. Rare work considers the data distribution and the topological structure of latent codes simultaneously, which often results in inferior embeddings in real-world graph data. This paper proposes a novel Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) method for attributed graph data to improve the stability and quality of learned representations to tackle the crowding problem. The node-to-node geodesic similarity is preserved between the original and latent space under a pre-defined distribution. The proposed method surpasses state-of-the-art baseline algorithms by a significant margin on different downstream tasks across popular datasets, which validates our solutions. We promise to release the code after acceptance. 

Deep Manifold Graph Auto-Encoder For Attributed Graph Embedding

In the field of artificial intelligence for science, it is consistently an essential challenge to face a limited amount of labeled data for real-world problems. The prevailing approach is to pretrain a powerful task-agnostic model on a large unlabeled corpus but may struggle to transfer knowledge to downstream tasks. In this study, we propose InstructMol, a semi-supervised learning algorithm, to take better advantage of unlabeled examples. It introduces an instructor model to provide the confidence ratios as the measurement of pseudo-labels' reliability. These confidence scores then guide the target model to pay distinct attention to different data points, avoiding the over-reliance on labeled data and the negative influence of incorrect pseudo-annotations. Comprehensive experiments show that InstructBio substantially improves the generalization ability of molecular models, in not only molecular property predictions but also activity cliff estimations, demonstrating the superiority of the proposed method. Furthermore, our evidence indicates that InstructBio can be equipped with cutting-edge pretraining methods and used to establish large-scale and task-specific pseudo-labeled molecular datasets, which reduces the predictive errors and shortens the training process. Our work provides strong evidence that semi-supervised learning can be a promising tool to overcome the data scarcity limitation and advance molecular representation learning.

Stan Z. Li

Papers

Discovering and Explaining the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions

RFold: RNA Secondary Structure Prediction with Decoupled Optimization

Precipitation estimation based on infrared data with a spherical convolutional neural network

Deep Manifold Graph Auto-Encoder For Attributed Graph Embedding

InstructBio: A Large-scale Semi-supervised Learning Paradigm for Biochemical Problems