Jinhan Liu, Yibo Yang, Ruiying Lu, Piotr Piękos, Yimeng Chen, Peng Wang, Dandan Guo. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt to mitigate this via data selection, they typically rely on heuristic, instance-level assessments that neglect the global geometry of the data distribution and fail to explicitly repel harmful patterns. To address this, we introduce Safety Optimal Transport (SOT), a novel framework that reframes safe fine-tuning from an instance-level filtering challenge to a distribution-level alignment task grounded in Optimal Transport (OT). At its core is a dual-reference “push-pull” weight-learning mechanism: SOT optimizes sample importance by actively pulling the downstream distribution towards a trusted safe anchor while simultaneously pushing it away from a general harmful reference. This establishes a robust geometric safety boundary that effectively purifies the training data. Extensive experiments across diverse model families and domains demonstrate that SOT significantly enhances model safety while maintaining competitive downstream performance, achieving a superior safety-utility trade-off compared to baselines.

Tabular data have been playing a mostly important role in diverse real-world fields, such as healthcare, engineering, finance, etc. The recent success of deep learning has fostered many deep networks (e.g., Transformer, ResNet) based tabular learning methods. Generally, existing deep tabular machine learning methods are along with the two paradigms, i.e., in-learning and pre-learning. In-learning methods need to train networks from scratch or impose extra constraints to regulate the representations which nonetheless train multiple tasks simultaneously and make learning more difficult, while pre-learning methods design several pretext tasks for pre-training and then conduct task-specific fine-tuning, which however need much extra training effort with prior knowledge. In this paper, we introduce a novel deep Tabular Representation Corrector, TRC, to enhance any trained deep tabular model's representations without altering its parameters in a model-agnostic manner. Specifically, targeting the representation shift and representation redundancy that hinder prediction, we propose two tasks, i.e., (i) Tabular Representation Re-estimation, that involves training a shift estimator to calculate the inherent shift of tabular representations to subsequently mitigate it, thereby re-estimating the representations and (ii) Tabular Space Mapping, that transforms the above re-estimated representations into a light-embedding vector space via a coordinate estimator while preserves crucial predictive information to minimize redundancy. The two tasks jointly enhance the representations of deep tabular models without touching on the original models thus enjoying high efficiency. Finally, we conduct extensive experiments on state-of-the-art deep tabular machine learning models coupled with TRC on various tabular benchmarks which have shown consistent superiority.

In recent years, deep neural networks (DNNs) have demonstrated state-of-the-art performance across various domains. However, despite their success, they often face calibration issues, particularly in safety-critical applications such as autonomous driving and healthcare, where unreliable predictions can have serious consequences. Recent research has started to improve model calibration from the view of the classifier. However, the exploration of designing the classifier to solve the model calibration problem is insufficient. Let alone most of the existing methods ignore the calibration errors arising from underconfidence. In this work, we propose a novel method by Balancing learnable and ETF classifiers to solve the overconfidence or un-derconfidence problem for model CALibration named Bal-CAL. By introducing a confidence-tunable module and a dynamic adjustment method, we ensure better alignment between model confidence and its true accuracy. Extensive experimental validation shows that ours significantly improves model calibration performance while maintaining high predictive accuracy, outperforming existing techniques. This provides a novel solution to the calibration challenges commonly encountered in deep learning. Our code is available at BalCAL.

Fine-tuning vision-language models (VLMs) with large amounts of unlabeled data has recently garnered significant interest. However, a key challenge remains the lack of high-quality pseudo-labeled data. Current pseudo-labeling strategies often struggle with mismatches between semantic and visual information, leading to sub-optimal performance of unsupervised prompt learning (UPL) methods. In this paper, we introduce a simple yet effective approach called Augmenting Discriminative Richness via Diffusions (AiR), toward learning a richer discriminating way to represent the class comprehensively and thus facilitate classification. Specifically, our approach includes a pseudo-label generation module that leverages high-fidelity synthetic samples to create an auxiliary classifier, which captures richer visual variation, bridging text-image-pair classification to a more robust image-image-pair classification. Additionally, we exploit the diversity of diffusion-based synthetic samples to enhance prompt learning, providing greater information for semantic-visual alignment. Extensive experiments on five public benchmarks, including RESISC45 and Flowers102, and across three learning paradigms-UL, SSL, and TRZSL-demonstrate that AiR achieves substantial and consistent performance improvements over state-of-the-art unsupervised prompt learning methods. Code is available.

Federated Learning (FL) has emerged as a promising framework for distributed machine learning, enabling collaborative model training without sharing local data, thereby preserving privacy and enhancing security. However, data heterogeneity resulting from differences across user behav-iors, preferences, and device characteristics poses a significant challenge for federated learning. Most previous works overlook the adjustment of aggregation weights, relying solely on dataset size for weight assignment, which often leads to unstable convergence and reduced model performance. Recently, several studies have sought to refine aggregation strategies by incorporating dataset characteristics and model alignment. However, adaptively adjusting aggregation weights while ensuring data security—without requiring additional proxy data—remains a significant challenge. In this work, we propose Federated learning with Adaptive Weight Aggregation (FedAWA), a novel method that adaptively adjusts aggregation weights based on client vectors during the learning process. The client vector captures the direction of model updates, reflecting local data variations, and is used to optimize the aggregation weight without requiring additional datasets or violating privacy. By assigning higher aggregation weights to local models whose updates align closely with the global optimization direction, FedAWA enhances the stability and generalization of the global model. Extensive experiments under diverse scenarios demonstrate the superiority of our method, providing a promising solution to the challenges of data heterogeneity in federated learning.

The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning, where the Bradley-Terry (BT) objective has been recognized as simple yet powerful, specifically for pairwise preference learning.However, BT-based RMs often struggle to effectively distinguish between similar preference responses, leading to insufficient separation between preferred and non-preferred outputs.Consequently, they may easily overfit easy samples and cannot generalize well to Out-Of-Distribution (OOD) samples, resulting in suboptimal performance.To address these challenges, this paper introduces an effective enhancement to BT-based RMs through an adaptive margin mechanism.Specifically, we design to dynamically adjust the RM focus on more challenging samples through margins, based on both semantic similarity and model-predicted reward differences, which is approached from a distributional perspective solvable with Optimal Transport (OT).By incorporating these factors into a principled OT cost matrix design, our adaptive margin enables the RM to better capture distributional differences between chosen and rejected responses, yielding significant improvements in performance, convergence speed, and generalization capabilities.Experimental results across multiple benchmarks demonstrate that our method outperforms several existing RM techniques, showcasing enhanced performance in both In-Distribution (ID) and OOD settings.Moreover, RLHF experiments support our practical effectiveness in better aligning LLMs with human preferences.

In Federated Learning (FL), weighted aggregation of local models is conducted to generate a new global model, and the aggregation weights are typically normalized to 1. A recent study identifies the global weight shrinking effect in FL, indicating an enhancement in the global model’s generalization when the sum of weights (i.e., the shrinking factor) is smaller than 1, where how to learn the shrinking factor becomes crucial. However, principled approaches to this solution have not been carefully studied from the adequate consideration of privacy concerns and layer-wise distinctions. To this end, we propose a novel model aggregation strategy, Federated Learning with Adaptive Layer-wise Weight Shrinking (FedLWS), which adaptively designs the shrinking factor in a layer-wise manner and avoids optimizing the shrinking factors on a proxy dataset. We initially explored the factors affecting the shrinking factor during the training process. Then we calculate the layer-wise shrinking factors by considering the distinctions among each layer of the global model. FedLWS can be easily incorporated with various existing methods due to its flexibility. Extensive experiments under diverse scenarios demonstrate the superiority of our method over several state-of-the-art approaches, providing a promising tool for enhancing the global model in FL.

Anomaly detection, indicating to identify the anomalies that significantly deviate from the majority normal instances of data, has been an important role in machine learning and related applications. Despite the significant success achieved in anomaly detection on image and text data, the accurate Tabular Anomaly Detection (TAD) has still been hindered due to the lack of clear prior semantic information in the tabular data. Most state-of-the-art TAD studies are along the line of reconstruction, which first reconstruct training data and then use reconstruction errors to decide anomalies; however, reconstruction on training data can still hardly distinguish anomalies due to the data entanglement in their representations. To address this problem, in this paper, we propose a novel approach Decomposed Representation Learning (DRL), to re-map data into a tailor-designed constrained space, in order to capture the underlying shared patterns of normal samples and differ anomalous patterns for TAD. Specifically, we enforce the representation of each normal sample in the latent space to be decomposed into a weighted linear combination of randomly generated orthogonal basis vectors, where these basis vectors are both data-free and training-free. Furthermore, we enhance the discriminative capability between normal and anomalous patterns in the latent space by introducing a novel constraint that amplifies the discrepancy between these two categories, supported by theoretical analysis. Finally, extensive experiments on 40 tabular datasets and 16 competing tabular anomaly detection algorithms show that our method achieves state-of-the-art performance.

Tabular data have been playing a vital role in diverse real-world fields, including healthcare, finance, etc. With the recent success of Large Language Models (LLMs), early explorations of extending LLMs to the domain of tabular data have been developed. Most of these LLM-based methods typically first serialize tabular data into natural language descriptions, and then tune LLMs or directly infer on these serialized data. However, these methods suffer from two key inherent issues: (i) data perspective: existing data serialization methods lack universal applicability for structured tabular data, and may pose privacy risks through direct textual exposure, and (ii) model perspective: LLM fine-tuning methods struggle with tabular data, and in-context learning scalability is bottle-necked by input length constraints (suitable for few-shot learning). This work explores a novel direction of integrating LLMs into tabular data through logical decision tree rules as intermediaries, proposing a decision tree enhancer with LLM-derived rule for tabular prediction, DeLTa. The proposed DeLTa avoids tabular data serialization, and can be applied to full data learning setting without LLM fine-tuning. Specifically, we leverage the reasoning ability of LLMs to redesign an improved rule given a set of decision tree rules. Furthermore, we provide a calibration method for original decision trees via new generated rule by LLM, which approximates the error correction vector to steer the original decision tree predictions in the direction of ``errors'' reducing. Finally, extensive experiments on diverse tabular benchmarks show that our method achieves state-of-the-art performance.

Real-world datasets usually suffer from class imbalance and label noise. To solve the joint challenge of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy from clean samples. While effective, they may be limited in handling the joint issue in a unified way. In this work, we bridge this gap by effectively extracting a clean training subset from the noisy and long-tailed dataset, where we develop a novel re-labeling method using class prototypes from the perspective of distribution matching that can be solved with optimal transport. By using the learned transport plan to re-label training samples and setting a class-specific probability measure, our method can simultaneously reduce the side-effects of label noise and data imbalance during label refinement. Then we introduce a simple yet effective filter by combining the observed and refined labels to obtain a clean subset for robust model training. Comprehensive experiments show that our method can effectively extract clean subsets and bring significant performance gains in noisy long-tailed classification. Code is available athttps://github.com/BIRlz/NLT_prototype_clean_subset_extraction

Prompt tuning has been successfully used in leveraging the knowledge of Large-scale Vision-Language Pre-trained (VLP) models on downstream tasks. Most existing prompt tuning approaches learn prompts by maximizing the pairwise similarity. Although samples in different modalities might be relatively aligned pairwisely, such alignment does not fully utilize the information between samples, which can be less consistent on the modality level. In this paper, we propose a novel prompt tuning strategy by distributionally matching different modalities. Specifically, we minimize the distribution-wise distance between the image and text modalities with optimal transport (OT) theory. Simultaneously, we add a constraint on the learned transport plan during the modality matching to enhance the learning of vision and text prompts. Our proposed one can be applied to improve existing uni-modal and multi-modal prompt learning methods for being a plug-and-play method, which can generate modality-consistent representations. Experiments on eleven public datasets demonstrate that our proposed method has excellent performance, achieving substantial improvements on both uni-modal and multi-modal prompt tuning methods.

In recent years, impressive progress has been achieved in synthetic aperture radar (SAR)-based automatic target recognition (ATR) with the development of deep learning. In practice, a complete training SAR image dataset in all target-aspect domains is limited available for one measurement. When SAR images in the unseen aspect domains are newly acquired, direct retraining of the trained SAR-ATR models with them may lead to a significant performance decline for the seen aspect domains. In this article, we propose an aspect continual recognition model (ACRM) to address the learned feature forgetting problem when SAR images with different target aspects come sequentially in the real-world SAR-ATR. Considering the abundant variations of SAR images with target aspects, we introduce the Bayesian probabilistic frame to improve the model’s generalization of characterizing the varied target features across different aspects. To acquire a better solution for the posterior probability of the model parameters, we integrate an online Monte Carlo variational inference into the deep neural network in the ACRM. Furthermore, to mitigate the accumulation of estimation errors caused by the repetitive approximations in inference, we leverage the coreset method by retaining a small subset of important samples from previous tasks as a coreset. We conduct extensive experiments on the MSTAR and FUSARship datasets. Compared with a variety of baseline algorithms in continual learning, our methods exhibit excellent SAR-ATR performance and robustness, when the SAR images from different target aspects are acquired sequentially.

Change point detection is crucial for identifying state transitions and anomalies in dynamic systems, with applications in network security, health care, and social network analysis. Dynamic systems are represented by dynamic graphs with spatial and temporal dimensions. As objects and their relations in a dynamic graph change over time, detecting these changes is essential. Numerous methods for change point detection in dynamic graphs have been developed, but no systematic review exists. This paper addresses this gap by introducing change point detection tasks in dynamic graphs, discussing two tasks based on input data types: detection in graph snapshot series (focusing on graph topology changes) and time series on graphs (focusing on changes in graph entities with temporal dynamics). We then present related challenges and applications, provide a comprehensive taxonomy of surveyed methods, including datasets and evaluation metrics, and discuss promising research directions.

Tabular data have been playing a mostly important role in diverse real-world fields, such as healthcare, engineering, finance, etc. With the recent success of deep learning, many tabular machine learning (ML) methods based on deep networks (e.g., Transformer, ResNet) have achieved competitive performance on tabular benchmarks. However, existing deep tabular ML methods suffer from the representation entanglement and localization, which largely hinders their prediction performance and leads to performance inconsistency on tabular tasks. To overcome these problems, we explore a novel direction of applying prototype learning for tabular ML and propose a prototype-based tabular representation learning framework, PTaRL, for tabular prediction tasks. The core idea of PTaRL is to construct prototype-based projection space (P-Space) and learn the disentangled representation around global data prototypes. Specifically, PTaRL mainly involves two stages: (i) Prototype Generating, that constructs global prototypes as the basis vectors of P-Space for representation, and (ii) Prototype Projecting, that projects the data samples into P-Space and keeps the core global data information via Optimal Transport. Then, to further acquire the disentangled representations, we constrain PTaRL with two strategies: (i) to diversify the coordinates towards global prototypes of different representations within P-Space, we bring up a diversifying constraint for representation calibration; (ii) to avoid prototype entanglement in P-Space, we introduce a matrix orthogonalization constraint to ensure the independence of global prototypes. Finally, we conduct extensive experiments in PTaRL coupled with state-of-the-art deep tabular ML models on various tabular benchmarks and the results have shown our consistent superiority.

A well-trained deep neural network on balanced datasets usually exhibits the Neural Collapse (NC) phenomenon, which is an informative indicator of the model achieving good performance. However, NC is usually hard to be achieved for a model trained on long-tailed datasets, leading to the deteriorated performance of test data. This work aims to induce the NC phenomenon in imbalanced learning from the perspective of distribution matching. By enforcing the distribution of last-layer representations to align the ideal distribution of the ETF structure, we develop a Distribution Alignment Optimization (DisA) loss, acting as a plug-and-play method can be combined with most of the existing long-tailed methods, we further instantiate it to the cases of fixing classifier and learning classifier. The extensive experiments show the effectiveness of DisA, providing a promising solution to the imbalanced issue. Our code is available at DisA.

In real-world synthetic aperture radar (SAR)-based automatic target recognition (ATR), variations in the target-aspect lead to differences in the distribution of target’s scattering points, which will affect the model’s recognition performance, if the training SAR images are incomplete among target-aspect. Traditional deep learning methods for SAR-based recognition often suffer from catastrophic forgetting when online trained on SAR images from different target-aspect domains. To equip SAR-ATR models with the capability of recognizing SAR images online from subsequent target-aspect domains and retaining previously learned knowledge with minimal forgetting, we propose a target-aspect hard attention continual learning (THAT-CL) method, which applies a hard attention mechanism through embedding the indexes of different target-aspect recognition tasks as vectors in each network layer to memorize information of different tasks. By dynamically scaling network weight gradients, we ensure that weights containing more task-specific information undergo smaller updates, while weights with less relevant information experience larger updates. We evaluate THAT-CL using the moving and stationary target acquisition and recognition (MSTAR) dataset. Comparative analysis against other methods demonstrates that the network with THAT-CL achieves higher average accuracy of 93.58% and lower forgetting rate of 3.01%. The results highlight the excellent recognition capability of THAT-CL in generalizing across different SAR image target recognition tasks with varying target-aspects.

Training on disjoint fixed-length segments, Transformers convert static word embeddings into contextualized word representations. However, they often restrict the context of a token to the segment it resides in and hence neglect the contextual information across segments, failing to capture longer-term dependencies beyond the predefined segment length. This article uses a probabilistic deep topic model to provide hierarchical contextualized embeddings at both the token and segment levels, and integrate topic information through a constrained attention mechanism. The proposed method not only injects contextualized topic information into Transformers, but also controls languages generation guided by specific topics, styles, and sentiments. Three plug-and-play modules are proposed, including the contextual topical token embedding, the segment embedding, and the multi-head topic attention mechanism. We aim to capture the semantic coherence and word concurrence patterns at the global level, and also enrich the representation of each token by adapting to its local context, with negligible increased memory footprint and computational time. Experiments on various corpora show that by adding marginal extra parameters, the proposed hierarchical topic-aware contextualized Transformers consistently outperform their conventional counterparts, and generate sentences and paragraphs according to human preferences.

As machine learning algorithms are increasingly deployed for high-impact automated decision-making, the presence of bias (in datasets or tasks) gradually becomes one of the most critical challenges in machine learning applications. Such challenges range from the bias of race in face recognition to the bias of gender in hiring systems, where race and gender can be denoted as sensitive attributes. In recent years, much progress has been made in ensuring fairness and reducing bias in standard machine learning settings. Among them, learning fair representations with respect to the sensitive attributes has attracted increasing attention due to its flexibility in learning the rich representations based on advances in deep learning. In this article, we propose graph-fair, an algorithmic approach to learning fair representations under the graph Laplacian regularization, which reduces the separation between groups and the clustering within a group by encoding the sensitive attribute information into the graph. We have theoretically proved the underlying connection between graph regularization and distance correlation and show that the latter can be regarded as a standardized version of the former, with an additional advantage of being scale-invariant. Therefore, we naturally adopt the distance correlation as the fairness constraint to decrease the dependence between sensitive attributes and latent representations, called dist-fair. In contrast to existing approaches using measures of dependency and adversarial generators, both graph-fair and dist-fair provide simple fairness constraints, which eliminate the need for parameter tuning (e.g., choosing kernels) and introducing adversarial networks. Experiments conducted on real-world corpora indicate that our proposed fairness constraints applied for representation learning can provide better tradeoffs between fairness and utility results than existing approaches.

Cross-domain named entity recognition (NER), aiming to address the limitation of labeled resources in the target domain, is a challenging yet important task. Most existing studies alleviate the data discrepancy across different domains at the coarse level via combing NER with language modelings or introducing domain-adaptive pre-training (DAPT). Notably, source and target domains tend to share more fine-grained local information within denser subsequences than global information within the whole sequence, such that subsequence features are easier to transfer, which has not been explored well. Besides, compared to token-level representation, subsequence-level information can help the model distinguish different meanings of the same word in different domains. In this paper, we propose to incorporate subsequence-level features for promoting the cross-domain NER. In detail, we first utilize a pre-trained encoder to extract the global information. Then, we re-express each sentence as a group of subsequences and propose a novel bidirectional memory recurrent unit (BMRU) to capture features from the subsequences. Finally, an adaptive coupling unit (ACU) is proposed to combine global information and subsequence features for predicting entity labels. Experimental results on several benchmark datasets illustrate the effectiveness of our model, which achieves considerable improvements.

Real-world data usually confronts severe class-imbalance problems, where several majority classes have a significantly larger presence in the training set than minority classes. One effective solution is using mixup-based methods to generate synthetic samples to enhance the presence of minority classes. Previous approaches mix the background images from the majority classes and foreground images from the minority classes in a random manner, which ignores the sample-level semantic similarity, possibly resulting in less reasonable or less useful images. In this work, we propose an adaptive image-mixing method based on optimal transport (OT) to incorporate both class-level and sample-level information, which is able to generate semantically reasonable and meaningful mixed images for minority classes. Due to its flexibility, our method can be combined with existing long-tailed classification methods to enhance their performance and it can also serve as a general data augmentation method for balanced datasets. Extensive experiments indicate that our method achieves effective performance for long-tailed classification tasks. The code is available at https://github.com/JintongGao/Enhancing-Minority-Classes-by-Mixing.

Millimeter-wave (MMW) imaging techniques have been widely used in the public security industries for their under-controlled privacy concerns and no health hazards. However, since MMW images are low resolution and most objects are small, reflection-weak, diverse, suspicious object detection in the MMW images is a very challenging task. This paper develops a robust suspicious object detector for the MMW images based on the Siamese network integrated with the pose estimation and image segmentation, which estimates the coordinates of human joints and segments the complete human images into symmetrical body part images. Unlike most existing detectors, which detect and recognize suspicious objects in MMW images and require a complete training set with correct annotations, our proposed model aims to learn the similarity between two symmetrical human body part images segmented from the complete MMW images. Furthermore, to decrease the misdetection caused by the restricted field of view, we further fuse the multi-view MMW images observed from the same person by designing a decision-level fusion strategy and feature-level fusion strategy based on the attention mechanism. Experimental results on the measured MMW images show that our proposed models have favorable detection accuracy and speed in practical application and thus prove their effectiveness.

Imbalanced data pose challenges for deep learning based classification models. One of the most widely-used approaches for tackling imbalanced data is re-weighting, where training samples are associated with different weights in the loss function. Most of existing re-weighting approaches treat the example weights as the learnable parameter and optimize the weights on the meta set, entailing expensive bilevel optimization. In this paper, we propose a novel re-weighting method based on optimal transport (OT) from a distributional point of view. Specifically, we view the training set as an imbalanced distribution over its samples, which is transported by OT to a balanced distribution obtained from the meta set. The weights of the training samples are the probability mass of the imbalanced distribution andlearned by minimizing the OT distance between the two distributions. Compared with existing methods, our proposed one disengages the dependence of the weight learning on the concerned classifier at each iteration. Experiments on image, text and point cloud datasets demonstrate that our proposed re-weighting method has excellent performance, achieving state-of-the-art results in many cases andproviding a promising tool for addressing the imbalanced classification issue. The code has been made available athttps://github.com/DandanGuo1993/reweight-imbalance-classification-with-OT.

Few-shot classification aims to learn a classifier to recognize unseen classes during training, where the learned model can easily become over-fitted based on the biased distribution formed by only a few training examples. A recent solution to this problem is calibrating the distribution of these few sample classes by transferring statistics from the base classes with sufficient examples, where how to decide the transfer weights from base classes to novel classes is the key. However, principled approaches for learning the transfer weights have not been carefully studied. To this end, we propose a novel distribution calibration method by learning the adaptive weight matrix between novel samples and base classes, which is built upon a hierarchical Optimal Transport (H-OT) framework. By minimizing the high-level OT distance between novel samples and base classes, we can view the learned transport plan as the adaptive weight information for transferring the statistics of base classes. The learning of the cost function between a base class and novel class in the high-level OT leads to the introduction of the low-level OT, which considers the weights of all the data samples in the base class. Experimental results on standard benchmarks demonstrate that our proposed plug-and-play model outperforms competing approaches and owns desired cross-domain generalization ability, indicating the effectiveness of the learned adaptive weights.

In recent years, deep neural networks are increasingly popular in the field of radar high-resolution range profiles (HRRPs) target recognition. Unfortunately, recent researches have revealed that a deep-learning classifier can be easily fooled by adding small perturbations to the input, named adversarial attack. This provides us an inspiration for radar deceptive jamming signal generation in electronic countermeasures (ECMs). However, the perturbations generated by these adversarial attacks are usually of complex envelopes and quite low power, making it challenging for jammers to generate such actual jamming signals. To solve that issue, we propose a practical deceptive jamming generation method that learns the vulnerable range cells in an HRRP sample and injects several jamming pulses with specific amplitudes into these range cells. Such jamming signals are easy to generate and can deceive the radar automatic target recognition (RATR) model to output the wrong target category prediction with high confidence. To avoid the requirement of the recognition network structure information, we leverage the differential evolution optimization algorithm (non-gradientbased). Further, to provide the potential of real-time jamming signal generation during the test, an encoder is constructed not only to learn the separable features but also to find the vulnerable range cells and the specific amplitudes of the jamming pulses. In the experiments, we apply the proposed attack algorithms to fool the one-dimensional convolutional neural network-based HRRPRATR models. The extensive experimental results on measured aircraft HRRP dataset prove that the proposed algorithms achieve a promising attack performance and serve as a practical and fast deceptive jamming generation method.

To build a flexible and interpretable model for document analysis, we develop deep autoencoding topic model (DATM) that uses a hierarchy of gamma distributions to construct its multi-stochastic-layer generative network. In order to provide scalable posterior inference for the parameters of the generative network, we develop topic-layer-adaptive stochastic gradient Riemannian MCMC that jointly learns simplex-constrained global parameters across all layers and topics, with topic and layer specific learning rates. Given a posterior sample of the global parameters, in order to efficiently infer the local latent representations of a document under DATM across all stochastic layers, we propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a Weibull distribution based stochastic downward generative model. To jointly model documents and their associated labels, we further propose supervised DATM that enhances the discriminative power of its latent representations. The efficacy and scalability of our models are demonstrated on both unsupervised and supervised learning tasks on big corpora.

To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation. Moving beyond a conventional RNN-based language model that ignores long-range word dependencies and sentence order, the proposed model captures not only intra-sentence word dependencies, but also temporal transitions between sentences and inter-sentence topic dependencies. For inference, we develop a hybrid of stochastic-gradient Markov chain Monte Carlo and recurrent autoencoding variational Bayes. Experimental results on a variety of real-world text corpora demonstrate that the proposed model not only outperforms larger-context RNN-based language models, but also learns interpretable recurrent multilayer topics and generates diverse sentences and paragraphs that are syntactically correct and semantically coherent.

We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies. Using sophisticated but simple-to-implement data augmentation techniques, we derived closed-form Gibbs sampling update equations by first backward and upward propagating auxiliary latent counts, and then forward and downward sampling latent variables. Moreover, we develop stochastic gradient MCMC inference that is scalable to very long multivariate count time series. Experiments on both synthetic and a variety of real-world data demonstrate that the proposed model not only has excellent predictive performance, but also provides highly interpretable multilayer latent structure to represent hierarchical and temporal information propagation.

BACKGROUND: Many plant pathogen secretory proteins are known to be elicitors or pathogenic factors,which play an important role in the host-pathogen interaction process. Bioinformatics approaches make possible the large scale prediction and analysis of secretory proteins from the Puccinia helianthi transcriptome. The internet-based software SignalP v4.1, TargetP v1.01, Big-PI predictor, TMHMM v2.0 and ProtComp v9.0 were utilized to predict the signal peptides and the signal peptide-dependent secreted proteins among the 35,286 ORFs of the P. helianthi transcriptome. RESULTS: 908 ORFs (accounting for 2.6% of the total proteins) were identified as putative secretory proteins containing signal peptides. The length of the majority of proteins ranged from 51 to 300 amino acids (aa), while the signal peptides were from 18 to 20 aa long. Signal peptidase I (SpI) cleavage sites were found in 463 of these putative secretory signal peptides. 55 proteins contained the lipoprotein signal peptide recognition site of signal peptidase II (SpII). Out of 908 secretory proteins, 581 (63.8%) have functions related to signal recognition and transduction, metabolism, transport and catabolism. Additionally, 143 putative secretory proteins were categorized into 27 functional groups based on Gene Ontology terms, including 14 groups in biological process, seven in cellular component, and six in molecular function. Gene ontology analysis of the secretory proteins revealed an enrichment of hydrolase activity. Pathway associations were established for 82 (9.0%) secretory proteins. A number of cell wall degrading enzymes and three homologous proteins specific to Phytophthora sojae effectors were also identified, which may be involved in the pathogenicity of the sunflower rust pathogen. CONCLUSIONS: This investigation proposes a new approach for identifying elicitors and pathogenic factors. The eventual identification and characterization of 908 extracellularly secreted proteins will advance our understanding of the molecular mechanisms of interactions between sunflower and rust pathogen and will enhance our ability to intervene in disease states.