Search

Structural balance theory predicts that triads in networks gravitate towards stable configurations. The theory has been verified for undirected graphs. Since real-world networks are often directed, we introduce a novel method for considering both transitivity and sign consistency for evaluating partial balance in signed digraphs. We test our approach on graphs constructed by using different methods for identifying edge signs: natural language processing to infer signs from underlying text data, and self-reported survey data. Our results show that for various social contexts and edge sign detection methods, partial balance of these digraphs are moderately high, ranging from 61% to 96%. Our approach not only enhances the theoretical framework of structural balance but also provides practical insights into the stability of social networks, enabling a deeper understanding of interpersonal and group dynamics across different communication platforms., Comment: arXiv admin note: text overlap with arXiv:2006.02565

Training models with varying capacities can be advantageous for deploying them in different scenarios. While high-capacity models offer better performance, low-capacity models require fewer computing resources for training and inference. In this work, we propose a novel one-stop training framework to jointly train high-capacity and low-capactiy models. This framework consists of two composite model architectures and a joint training algorithm called Two-Stage Joint-Training (TSJT). Unlike knowledge distillation, where multiple capacity models are trained from scratch separately, our approach integrates supervisions from different capacity models simultaneously, leading to faster and more efficient convergence. Extensive experiments on the multilingual machine translation benchmark WMT10 show that our method outperforms low-capacity baseline models and achieves comparable or better performance on high-capacity models. Notably, the analysis demonstrates that our method significantly influences the initial training process, leading to more efficient convergence and superior solutions.

MRI synthesis promises to mitigate the challenge of missing MRI modality in clinical practice. Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions. However, most diffusion-based MRI synthesis models are using a single modality. As they operate in the original image domain, they are memory-intensive and less feasible for multi-modal synthesis. Moreover, they often fail to preserve the anatomical structure in MRI. Further, balancing the multiple conditions from multi-modal MRI inputs is crucial for multi-modal synthesis. Here, we propose the first diffusion-based multi-modality MRI synthesis model, namely Conditioned Latent Diffusion Model (CoLa-Diff). To reduce memory consumption, we design CoLa-Diff to operate in the latent space. We propose a novel network architecture, e.g., similar cooperative filtering, to solve the possible compression and noise in latent space. To better maintain the anatomical structure, brain region masks are introduced as the priors of density distributions to guide diffusion process. We further present auto-weight adaptation to employ multi-modal information effectively. Our experiments demonstrate that CoLa-Diff outperforms other state-of-the-art MRI synthesis methods, promising to serve as an effective tool for multi-modal MRI synthesis., Comment: 8 pages

Multi-contrast magnetic resonance imaging (MRI) is the most common management tool used to characterize neurological disorders based on brain tissue contrasts. However, acquiring high-resolution MRI scans is time-consuming and infeasible under specific conditions. Hence, multi-contrast super-resolution methods have been developed to improve the quality of low-resolution contrasts by leveraging complementary information from multi-contrast MRI. Current deep learning-based super-resolution methods have limitations in estimating restoration uncertainty and avoiding mode collapse. Although the diffusion model has emerged as a promising approach for image enhancement, capturing complex interactions between multiple conditions introduced by multi-contrast MRI super-resolution remains a challenge for clinical applications. In this paper, we propose a disentangled conditional diffusion model, DisC-Diff, for multi-contrast brain MRI super-resolution. It utilizes the sampling-based generation and simple objective function of diffusion models to estimate uncertainty in restorations effectively and ensure a stable optimization process. Moreover, DisC-Diff leverages a disentangled multi-stream network to fully exploit complementary information from multi-contrast MRI, improving model interpretation under multiple conditions of multi-contrast inputs. We validated the effectiveness of DisC-Diff on two datasets: the IXI dataset, which contains 578 normal brains, and a clinical dataset with 316 pathological brains. Our experimental results demonstrate that DisC-Diff outperforms other state-of-the-art methods both quantitatively and visually., Comment: Early Accepted by MICCAI 2023

Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. However, they are still limited due to redundant attack search spaces and the inability to defend against various types of attacks. In this work, we present a novel fine-tuning approach called \textbf{RO}bust \textbf{SE}letive fine-tuning (\textbf{ROSE}) to address this issue. ROSE conducts selective updates when adapting pre-trained models to downstream tasks, filtering out invaluable and unrobust updates of parameters. Specifically, we propose two strategies: the first-order and second-order ROSE for selecting target robust parameters. The experimental results show that ROSE achieves significant improvements in adversarial robustness on various downstream NLP tasks, and the ensemble method even surpasses both variants above. Furthermore, ROSE can be easily incorporated into existing fine-tuning methods to improve their adversarial robustness further. The empirical analysis confirms that ROSE eliminates unrobust spurious updates during fine-tuning, leading to solutions corresponding to flatter and wider optima than the conventional method. Code is available at \url{https://github.com/jiangllan/ROSE}., Comment: Accepted to EMNLP 2022. Code is available at https://github.com/jiangllan/ROSE

Spreadsheets are among the most commonly used file formats for data management, distribution, and analysis. Their widespread employment makes it easy to gather large collections of data, but their flexible canvas-based structure makes automated analysis difficult without heavy preparation. One of the common problems that practitioners face is the presence of multiple, independent regions in a single spreadsheet, possibly separated by repeated empty cells. We define such files as "multiregion" files. In collections of various spreadsheets, we can observe that some share the same layout. We present the Mondrian approach to automatically identify layout templates across multiple files and systematically extract the corresponding regions. Our approach is composed of three phases: first, each file is rendered as an image and inspected for elements that could form regions; then, using a clustering algorithm, the identified elements are grouped to form regions; finally, every file layout is represented as a graph and compared with others to find layout templates. We compare our method to state-of-the-art table recognition algorithms on two corpora of real-world enterprise spreadsheets. Our approach shows the best performances in detecting reliable region boundaries within each file and can correctly identify recurring layouts across files.

Despite the remarkable success deep models have achieved in Textual Matching (TM) tasks, it still remains unclear whether they truly understand language or measure the semantic similarity of texts by exploiting statistical bias in datasets. In this work, we provide a new perspective to study this issue -- via the length divergence bias. We find the length divergence heuristic widely exists in prevalent TM datasets, providing direct cues for prediction. To determine whether TM models have adopted such heuristic, we introduce an adversarial evaluation scheme which invalidates the heuristic. In this adversarial setting, all TM models perform worse, indicating they have indeed adopted this heuristic. Through a well-designed probing experiment, we empirically validate that the bias of TM models can be attributed in part to extracting the text length information during training. To alleviate the length divergence bias, we propose an adversarial training method. The results demonstrate we successfully improve the robustness and generalization ability of models at the same time., Comment: Accepted to Findings of ACL 2022

Most tough hydrogels are reinforced by introducing sacrificial structures that can dissipate input energy. However, since the sacrificial damages cannot recover instantly, the toughness of these gels drops substantially during consecutive cyclic loadings. Here, we propose a new damageless reinforcement strategy for hydrogels utilizing strain-induced crystallization (SIC). In Slide-Ring (SR) gels with freely movable cross-links, crystalline repetitively forms and destructs with elongation and relaxation, resulting in both excellent toughness of 5.5 - 25.2 MJ/m$^3$ and 87% - 95% instant recovery of extension energy between two consecutive 11-fold loading-unloading cycles. Moreover, SIC occurs "on-demandly" at the crack-tip area where strain amplification and stress concentration take place and forces the crack to turn sideways. The instantly reversible tough hydrogels are promising candidates for applications in artificial connective tissues such as tendon and ligament., Comment: 33 pages, 9 figures

Structural balance theory assumes triads in networks to gravitate towards stable configurations. The theory has been verified for undirected graphs. Since real-world networks are often directed, we introduce a novel method for considering both transitivity and sign consistency for calculating balance in signed digraphs. We test our approach on graphs that we constructed by using different methods for identifying edge signs: natural language processing to infer signs from underlying text data, and self-reported survey data. Our results show that for various social contexts and edge sign detection methods, balance is moderately high, ranging from 67.5% to 92.4%., Comment: 27 pages including figures, tables, references

Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any linguistic annotation of phrase segmentation. Instead, we define syntactic heights and phrase segmentation rules, enabling the model to automatically induce phrases, recognize their task-specific heads, and generate phrase embeddings in an unsupervised learning manner. Our method can easily be applied to language models with different network architectures since an independent module is used for phrase induction and context-phrase alignment, and no change is required in the underlying language modeling network. Experiments have shown that our model outperformed several strong baseline models on different data sets. We achieved a new state-of-the-art performance of 17.4 perplexity on the Wikitext-103 dataset. Additionally, visualizing the outputs of the phrase induction module showed that our model is able to learn approximate phrase-level structural knowledge without any annotation., Comment: Accepted by ACL 2019

A new Bayesian state and parameter learning algorithm for multiple target tracking (MTT) models with image observations is proposed. Specifically, a Markov chain Monte Carlo algorithm is designed to sample from the posterior distribution of the unknown number of targets, their birth and death times, states and model parameters, which constitutes the complete solution to the tracking problem. The conventional approach is to pre-process the images to extract point observations and then perform tracking. We model the image generation process directly to avoid potential loss of information when extracting point observations. Numerical examples show that our algorithm has improved tracking performance over commonly used techniques, for both synthetic examples and real florescent microscopy data, especially in the case of dim targets with overlapping illuminated regions.

Automatic and adaptive approximation, optimization, or integration of functions in a cone with guarantee of accuracy is a relatively new paradigm. Our purpose is to create an open-source MATLAB package, Guaranteed Automatic Integration Library (GAIL), following the philosophy of reproducible research and sustainable practices of robust scientific software development. For our conviction that true scholarship in computational sciences are characterized by reliable reproducibility, we employ the best practices in mathematical research and software engineering known to us and available in MATLAB. This document describes the key features of functions in GAIL, which includes one-dimensional function approximation and minimization using linear splines, one-dimensional numerical integration using trapezoidal rule, and last but not least, mean estimation and multidimensional integration by Monte Carlo methods or Quasi Monte Carlo methods.

Simple Monte Carlo is a versatile computational method with a convergence rate of $O(n^{-1/2})$. It can be used to estimate the means of random variables whose distributions are unknown. Bernoulli random variables, $Y$, are widely used to model success (failure) of complex systems. Here $Y=1$ denotes a success (failure), and $p=\mathbb{E}(Y)$ denotes the probability of that success (failure). Another application of Bernoulli random variables is $Y=\mathbb{1}_{R}(\boldsymbol{X})$, where then $p$ is the probability of $\boldsymbol{X}$ lying in the region $R$. This article explores how estimate $p$ to a prescribed absolute error tolerance, $\varepsilon$, with a high level of confidence, $1-\alpha$. The proposed algorithm automatically determines the number of samples of $Y$ needed to reach the prescribed error tolerance with the specified confidence level by using Hoeffding's inequality. The algorithm described here has been implemented in MATLAB and is part of the Guaranteed Automatic Integration Library (GAIL).

We propose a new Bayesian tracking and parameter learning algorithm for non-linear non-Gaussian multiple target tracking (MTT) models. We design a Markov chain Monte Carlo (MCMC) algorithm to sample from the posterior distribution of the target states, birth and death times, and association of observations to targets, which constitutes the solution to the tracking problem, as well as the model parameters. In the numerical section, we present performance comparisons with several competing techniques and demonstrate significant performance improvements in all cases.

We present both offline and online maximum likelihood estimation (MLE) techniques for inferring the static parameters of a multiple target tracking (MTT) model with linear Gaussian dynamics. We present the batch and online versions of the expectation-maximisation (EM) algorithm for short and long data sets respectively, and we show how Monte Carlo approximations of these methods can be implemented. Performance is assessed in numerical examples using simulated data for various scenarios and a comparison with a Bayesian estimation procedure is also provided., Comment: 17 double column pages, 9 figures

Monte Carlo methods are used to approximate the means, $\mu$, of random variables $Y$, whose distributions are not known explicitly. The key idea is that the average of a random sample, $Y_1, ..., Y_n$, tends to $\mu$ as $n$ tends to infinity. This article explores how one can reliably construct a confidence interval for $\mu$ with a prescribed half-width (or error tolerance) $\varepsilon$. Our proposed two-stage algorithm assumes that the kurtosis of $Y$ does not exceed some user-specified bound. An initial independent and identically distributed (IID) sample is used to confidently estimate the variance of $Y$. A Berry-Esseen inequality then makes it possible to determine the size of the IID sample required to construct the desired confidence interval for $\mu$. We discuss the important case where $Y=f(\vX)$ and $\vX$ is a random $d$-vector with probability density function $\rho$. In this case $\mu$ can be interpreted as the integral $\int_{\reals^d} f(\vx) \rho(\vx) \dif \vx$, and the Monte Carlo method becomes a method for multidimensional cubature.