Benefit-aware early prediction of health outcomes on multivariate EEG time series.

Given a cardiac-arrest patient being monitored in the ICU (intensive care unit) for brain activity, how can we predict their health outcomes as early as possible? Early decision-making is critical in many applications, e.g. monitoring patients may assist in early intervention and improved care. On the other hand, early prediction on EEG data poses several challenges: (i) earliness-accuracy trade-off; observing more data often increases accuracy but sacrifices earliness, (ii) large-scale (for training) and streaming (online decision-making) data processing, and (iii) multi-variate (due to multiple electrodes) and multi-length (due to varying length of stay of patients) time series. Motivated by this real-world application, we present BeneFitter that infuses the incurred savings from an early prediction as well as the cost from misclassification into a unified domain-specific target called benefit. Unifying these two quantities allows us to directly estimate a single target (i.e. benefit), and importantly, (a) is efficient and fast, with training time linear in the number of input sequences, and can operate in real-time for decision-making, (b) can handle multi-variate and variable-length time-series, suitable for patient data, and (c) is effective, providing up to 2× time-savings with equal or better accuracy as compared to competitors.

RNA-FrameFlow: Flow Matching for de novo 3D RNA Backbone Design.

We introduce RNA-FrameFlow, the first generative model for 3D RNA backbone design. We build upon SE(3) flow matching for protein backbone generation and establish protocols for data preparation and evaluation to address unique challenges posed by RNA modeling. We formulate RNA structures as a set of rigid-body frames and associated loss functions which account for larger, more conformationally flexible RNA backbones (13 atoms per nucleotide) vs. proteins (4 atoms per residue). Toward tackling the lack of diversity in 3D RNA datasets, we explore training with structural clustering and cropping augmentations. Additionally, we define a suite of evaluation metrics to measure whether the generated RNA structures are globally self-consistent (via inverse folding followed by forward folding) and locally recover RNA-specific structural descriptors. The most performant version of RNA-FrameFlow generates locally realistic RNA backbones of 40-150 nucleotides, over 40% of which pass our validity criteria as measured by a self-consistency TM-score >= 0.45, at which two RNAs have the same global fold. Open-source code: https://github.com/rish-16/rna-backbone-design.

Deep Long-Tailed Learning: A Survey.

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning has emerged as a powerful recognition model for learning high-quality image representations and has led to remarkable breakthroughs in generic visual recognition. However, long-tailed class imbalance, a common problem in practical visual recognition tasks, often limits the practicality of deep network based recognition models in real-world applications, since they can be easily biased towards dominant classes and perform poorly on tail classes. To address this problem, a large number of studies have been conducted in recent years, making promising progress in the field of deep long-tailed learning. Considering the rapid evolution of this field, this article aims to provide a comprehensive survey on recent advances in deep long-tailed learning. To be specific, we group existing deep long-tailed learning studies into three main categories (i.e., class re-balancing, information augmentation and module improvement), and review these methods following this taxonomy in detail. Afterward, we empirically analyze several state-of-the-art methods by evaluating to what extent they address the issue of class imbalance via a newly proposed evaluation metric, i.e., relative accuracy. We conclude the survey by highlighting important applications of deep long-tailed learning and identifying several promising directions for future research.

CapMax: A Framework for Dynamic Network Representation Learning From the View of Multiuser Communication.

In this article, a modified mutual information maximization (InfoMax) framework, named channel capacity maximization (CapMax), is proposed and applied to learn informative representations for dynamic networks with time-varying topology and/or time-evolving node attributes. The CapMax is based on the network information theory for multiuser communication, where the representation model is treated as a multiaccess communication channel with memory and feedback. Without requirements of the backbone structure, the learning objective of our CapMax is maximizing the channel capacity, which is measured by directed information (DI) rather than mutual information. For efficient implementation, we design an estimator of the channel capacity through the combination of graph neural networks (GNNs) and recurrent neural networks (RNNs). Under some mild conditions, we theoretically prove that DI is a better measure than mutual information in capturing useful information. The experiments are conducted on multiple real-world dynamic network datasets, and the outperformance of our CapMax on different backbone models on link detection and prediction validates the effectiveness of modeling the representation model as a communication channel.

Detecting Group Anomalies in Tera-Scale Multi-Aspect Data via Dense-Subtensor Mining.

How can we detect fraudulent lockstep behavior in large-scale multi-aspect data (i.e., tensors)? Can we detect it when data are too large to fit in memory or even on a disk? Past studies have shown that dense subtensors in real-world tensors (e.g., social media, Wikipedia, TCP dumps, etc.) signal anomalous or fraudulent behavior such as retweet boosting, bot activities, and network attacks. Thus, various approaches, including tensor decomposition and search, have been proposed for detecting dense subtensors rapidly and accurately. However, existing methods suffer from low accuracy, or they assume that tensors are small enough to fit in main memory, which is unrealistic in many real-world applications such as social media and web. To overcome these limitations, we propose D-Cube, a disk-based dense-subtensor detection method, which also can run in a distributed manner across multiple machines. Compared to state-of-the-art methods, D-Cube is (1) Memory Efficient: requires up to 1,561× less memory and handles 1,000× larger data (2.6TB), (2) Fast: up to 7× faster due to its near-linear scalability, (3) Provably Accurate: gives a guarantee on the densities of the detected subtensors, and (4) Effective: spotted network attacks from TCP dumps and synchronized behavior in rating data most accurately.

Power-Hop: A Pervasive Observation for Real Complex Networks.

Complex networks have been shown to exhibit universal properties, with one of the most consistent patterns being the scale-free degree distribution, but are there regularities obeyed by the r-hop neighborhood in real networks? We answer this question by identifying another power-law pattern that describes the relationship between the fractions of node pairs C(r) within r hops and the hop count r. This scale-free distribution is pervasive and describes a large variety of networks, ranging from social and urban to technological and biological networks. In particular, inspired by the definition of the fractal correlation dimension D2 on a point-set, we consider the hop-count r to be the underlying distance metric between two vertices of the network, and we examine the scaling of C(r) with r. We find that this relationship follows a power-law in real networks within the range 2 ≤ r ≤ d, where d is the effective diameter of the network, that is, the 90-th percentile distance. We term this relationship as power-hop and the corresponding power-law exponent as power-hop exponent h. We provide theoretical justification for this pattern under successful existing network models, while we analyze a large set of real and synthetic network datasets and we show the pervasiveness of the power-hop.