Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, Xudong Liu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

MixUp (Zhang et al. 2017) is a recently proposed dataaugmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with such additional data is shown capable of significantly improving the predictive accuracy of the current art. The power of MixUp, however, is primarily established empirically and its working and effectiveness have not been explained in any depth. In this paper, we develop an understanding for MixUp as a form of “out-of-manifold regularization”, which imposes certain “local linearity” constraints on the model’s input space beyond the data manifold. This analysis enables us to identify a limitation of MixUp, which we call “manifold intrusion”. In a nutshell, manifold intrusion in MixUp is a form of under-fitting resulting from conflicts between the synthetic labels of the mixed-up examples and the labels of original training data. Such a phenomenon usually happens when the parameters controlling the generation of mixing policies are not sufficiently fine-tuned on the training data. To address this issue, we propose a novel adaptive version of MixUp, where the mixing policies are automatically learned from the data using an additional network and objective function designed to avoid manifold intrusion. The proposed regularizer, AdaMixUp, is empirically evaluated on several benchmark datasets. Extensive experiments demonstrate that AdaMixUp improves upon MixUp when applied to the current art of deep classification models.

We have developed an integrated suite of algorithms, statistical methods, and computer applications to support large-scale LC-MS-based gel-free shotgun profiling of complex protein mixtures using basic experimental procedures. The programs automatically detect and quantify large numbers of peptide peaks in feature-rich ion mass chromatograms, compensate for spurious fluctuations in peptide signal intensities and retention times, and reliably match related peaks across many different datasets. Application of this toolkit markedly facilitates pattern recognition and biomarker discovery in global comparative proteomic studies, simplifying mechanistic investigation of physiological responses and the detection of proteomic signatures of disease.

Clustering proteins into groups on the basis of their domain compositions provides insight into protein evolution.

We propose a novel coding framework for wireless relay channels based on rateless codes, which allows for a natural extension to multiple antenna and multiple relay settings. The relaying protocol is half-duplex, and relays independently choose when to collaborate, if at all. With a simulated fountain code based implementation of this framework, we show that the use of rateless codes is both robust and efficient when the channel state information is not available at the transmitters

This paper stands at the intersection of two distinct lines of research. One line is “holographic algorithms,” a powerful approach introduced by Valiant for solving various counting problems in computer science; the other is “normal factor graphs,” an elegant framework proposed by Forney for representing codes defined on graphs. We introduce the notion of holographic transformations for normal factor graphs, and establish a very general theorem, called the generalized Holant theorem, which relates a normal factor graph to its holographic transformation. We show that the generalized Holant theorem on the one hand underlies the principle of holographic algorithms, and on the other hand reduces to a general duality theorem for normal factor graphs, a special case of which was first proved by Forney. In the course of our development, we formalize a new semantics for normal factor graphs, which highlights various linear algebraic properties that potentially enable the use of normal factor graphs as a linear algebraic tool.