Large Language Models work quite well with general-purpose data and many tasks in Natural Language Processing. However, they show several limitations when used for a task such as domain-specific abstractive text summarization. This paper identifies three of those limitations as research problems in the context of abstractive text summarization: 1) Quadratic complexity of transformer-based models with respect to the input text length; 2) Model Hallucination, which is a model's ability to generate factually incorrect text; and 3) Domain Shift, which happens when the distribution of the model's training and test corpus is not the same. Along with a discussion of the open research questions, this paper also provides an assessment of existing state-of-the-art techniques relevant to domain-specific text summarization to address the research gaps.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
INFORMS
·
有偏
·
Learning
·
可辨認的
·
Graph Neural Networks (GNNs) are powerful tools for learning representations on graphs, such as social networks. However, their vulnerability to privacy inference attacks restricts their practicality, especially in high-stake domains. To address this issue, privacy-preserving GNNs have been proposed, focusing on preserving node and/or link privacy. This work takes a step back and investigates how GNNs contribute to privacy leakage. Through theoretical analysis and simulations, we identify message passing under structural bias as the core component that allows GNNs to \textit{propagate} and \textit{amplify} privacy leakage. Building upon these findings, we propose a principled privacy-preserving GNN framework that effectively safeguards both node and link privacy, referred to as dual-privacy preservation. The framework comprises three major modules: a Sensitive Information Obfuscation Module that removes sensitive information from node embeddings, a Dynamic Structure Debiasing Module that dynamically corrects the structural bias, and an Adversarial Learning Module that optimizes the privacy-utility trade-off. Experimental results on four benchmark datasets validate the effectiveness of the proposed model in protecting both node and link privacy while preserving high utility for downstream tasks, such as node classification.
In this work, we focus on the Bipartite Stochastic Block Model (BiSBM), a popular model for bipartite graphs with a community structure. We consider the high dimensional setting where the number $n_1$ of type I nodes is far smaller than the number $n_2$ of type II nodes. The recent work of Braun and Tyagi (2022) established a sufficient and necessary condition on the sparsity level $p_{max}$ of the bipartite graph to be able to recover the latent partition of type I nodes. They proposed an iterative method that extends the one proposed by Ndaoud et al. (2022) to achieve this goal. Their method requires a good enough initialization, usually obtained by a spectral method, but empirical results showed that the refinement algorithm doesn't improve much the performance of the spectral method. This suggests that the spectral achieves exact recovery in the same regime as the refinement method. We show that it is indeed the case by providing new entrywise bounds on the eigenvectors of the similarity matrix used by the spectral method. Our analysis extend the framework of Lei (2019) that only applies to symmetric matrices with limited dependencies. As an important technical step, we also derive an improved concentration inequality for similarity matrices.
In this paper, we extend the techniques used in our previous work to show that there exists a probabilistic Turing machine running within time $O(n^k)$ for all $k\in\mathbb{N}_1$ accepting a language $L_d$ which is different from any language in $\mathcal{P}$, and then to show that $L_d\in\mathcal{BPP}$, thus separating the complexity classes $\mathcal{P}$ and $\mathcal{BPP}$ (i.e., $\mathcal{P}\subsetneq\mathcal{BPP}$). Since the complexity class of {\em bounded error quantum polynomial-time} $\mathcal{BQP}$ contains the complexity class $\mathcal{BPP}$, i.e., $\mathcal{BPP}\subseteq\mathcal{BQP}$, we thus obtain the result that quantum computers are {\em rigorously powerful than} traditional computers. Namely, $\mathcal{P}\subsetneq\mathcal{BQP}$. We further show that (1). $\mathcal{P}\subsetneq\mathcal{RP}$; (2). $\mathcal{P}\subsetneq\text{co-}\mathcal{RP}$; (3). $\mathcal{P}\subsetneq\mathcal{ZPP}$. The result of $\mathcal{P}\subsetneq\mathcal{BPP}$ shows that {\em randomness} plays an essential role in probabilistic algorithm design. Specifically, we show that: (1). The number of random bits used by any probabilistic algorithm which accepts the language $L_d$ can not be reduced to $O(\log n)$; (2). There exits no efficient (complexity-theoretic) {\em pseudorandom generator} (PRG) $G:\{0,1\}^{O(\log n)}\rightarrow \{0,1\}^n$; (3). There exists no quick HSG $H:k(n)\rightarrow n$ such that $k(n)=O(\log n)$.
In this work, we construct a large-scale dataset for Ground-to-Aerial Person Search, named G2APS, which contains 31,770 images of 260,559 annotated bounding boxes for 2,644 identities appearing in both of the UAVs and ground surveillance cameras. To our knowledge, this is the first dataset for cross-platform intelligent surveillance applications, where the UAVs could work as a powerful complement for the ground surveillance cameras. To more realistically simulate the actual cross-platform Ground-to-Aerial surveillance scenarios, the surveillance cameras are fixed about 2 meters above the ground, while the UAVs capture videos of persons at different location, with a variety of view-angles, flight attitudes and flight modes. Therefore, the dataset has the following unique characteristics: 1) drastic view-angle changes between query and gallery person images from cross-platform cameras; 2) diverse resolutions, poses and views of the person images under 9 rich real-world scenarios. On basis of the G2APS benchmark dataset, we demonstrate detailed analysis about current two-step and end-to-end person search methods, and further propose a simple yet effective knowledge distillation scheme on the head of the ReID network, which achieves state-of-the-art performances on both of the G2APS and the previous two public person search datasets, i.e., PRW and CUHK-SYSU. The dataset and source code available on \url{//github.com/yqc123456/HKD_for_person_search}.
In this paper, we propose a novel layer-adaptive weight-pruning approach for Deep Neural Networks (DNNs) that addresses the challenge of optimizing the output distortion minimization while adhering to a target pruning ratio constraint. Our approach takes into account the collective influence of all layers to design a layer-adaptive pruning scheme. We discover and utilize a very important additivity property of output distortion caused by pruning weights on multiple layers. This property enables us to formulate the pruning as a combinatorial optimization problem and efficiently solve it through dynamic programming. By decomposing the problem into sub-problems, we achieve linear time complexity, making our optimization algorithm fast and feasible to run on CPUs. Our extensive experiments demonstrate the superiority of our approach over existing methods on the ImageNet and CIFAR-10 datasets. On CIFAR-10, our method achieves remarkable improvements, outperforming others by up to 1.0% for ResNet-32, 0.5% for VGG-16, and 0.7% for DenseNet-121 in terms of top-1 accuracy. On ImageNet, we achieve up to 4.7% and 4.6% higher top-1 accuracy compared to other methods for VGG-16 and ResNet-50, respectively. These results highlight the effectiveness and practicality of our approach for enhancing DNN performance through layer-adaptive weight pruning. Code will be available on //github.com/Akimoto-Cris/RD_VIT_PRUNE.
The Type-I and Type-II censoring schemes are the most prominent and commonly used censoring schemes in practice. In this work, a mixture of Type-I and Type- II censoring schemes, named the Type I-Type II mixture censoring scheme, has been introduced. Different censoring schemes have been discussed, along with their benefits and drawbacks. For the proposed censoring scheme, we analyze the data under the assumption that failure times of experimental units follow the Weibull distribution. The computational formulas for the expected number of failures and the expected failure time are provided. Maximum likelihood estimation and Bayesian estimation are used to estimate the model parameters. On the basis of thorough Monte Carlo simulations, the investigated inferential approaches are evaluated. Finally, a numerical example is provided to demonstrate the method of inference discussed here.
Transformers have achieved superior performances in many tasks in natural language processing and computer vision, which also intrigues great interests in the time series community. Among multiple advantages of transformers, the ability to capture long-range dependencies and interactions is especially attractive for time series modeling, leading to exciting progress in various time series applications. In this paper, we systematically review transformer schemes for time series modeling by highlighting their strengths as well as limitations through a new taxonomy to summarize existing time series transformers in two perspectives. From the perspective of network modifications, we summarize the adaptations of module level and architecture level of the time series transformers. From the perspective of applications, we categorize time series transformers based on common tasks including forecasting, anomaly detection, and classification. Empirically, we perform robust analysis, model size analysis, and seasonal-trend decomposition analysis to study how Transformers perform in time series. Finally, we discuss and suggest future directions to provide useful research guidance. To the best of our knowledge, this paper is the first work to comprehensively and systematically summarize the recent advances of Transformers for modeling time series data. We hope this survey will ignite further research interests in time series Transformers.
Recommender systems have been widely applied in different real-life scenarios to help us find useful information. Recently, Reinforcement Learning (RL) based recommender systems have become an emerging research topic. It often surpasses traditional recommendation models even most deep learning-based methods, owing to its interactive nature and autonomous learning ability. Nevertheless, there are various challenges of RL when applying in recommender systems. Toward this end, we firstly provide a thorough overview, comparisons, and summarization of RL approaches for five typical recommendation scenarios, following three main categories of RL: value-function, policy search, and Actor-Critic. Then, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommendation, we highlight some potential research directions in this field.
Connecting Vision and Language plays an essential role in Generative Intelligence. For this reason, in the last few years, a large research effort has been devoted to image captioning, i.e. the task of describing images with syntactically and semantically meaningful sentences. Starting from 2015 the task has generally been addressed with pipelines composed of a visual encoding step and a language model for text generation. During these years, both components have evolved considerably through the exploitation of object regions, attributes, and relationships and the introduction of multi-modal connections, fully-attentive approaches, and BERT-like early-fusion strategies. However, regardless of the impressive results obtained, research in image captioning has not reached a conclusive answer yet. This work aims at providing a comprehensive overview and categorization of image captioning approaches, from visual encoding and text generation to training strategies, used datasets, and evaluation metrics. In this respect, we quantitatively compare many relevant state-of-the-art approaches to identify the most impactful technical innovations in image captioning architectures and training strategies. Moreover, many variants of the problem and its open challenges are analyzed and discussed. The final goal of this work is to serve as a tool for understanding the existing state-of-the-art and highlighting the future directions for an area of research where Computer Vision and Natural Language Processing can find an optimal synergy.
Machine learning techniques have deeply rooted in our everyday life. However, since it is knowledge- and labor-intensive to pursue good learning performance, human experts are heavily involved in every aspect of machine learning. In order to make machine learning techniques easier to apply and reduce the demand for experienced human experts, automated machine learning (AutoML) has emerged as a hot topic with both industrial and academic interest. In this paper, we provide an up to date survey on AutoML. First, we introduce and define the AutoML problem, with inspiration from both realms of automation and machine learning. Then, we propose a general AutoML framework that not only covers most existing approaches to date but also can guide the design for new methods. Subsequently, we categorize and review the existing works from two aspects, i.e., the problem setup and the employed techniques. Finally, we provide a detailed analysis of AutoML approaches and explain the reasons underneath their successful applications. We hope this survey can serve as not only an insightful guideline for AutoML beginners but also an inspiration for future research.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191