检索结果-内蒙古大学图书馆

Visual Transformation Telling

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cui, Wanqing Hong, Xin Lan, Yanyan Pang, Liang Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Data Intelligence System Research Center Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China

Humans can naturally reason from superficial state differences (e.g. ground wetness) to transformations descriptions (e.g. raining) according to their life experience. In this paper, we propose a new visual reasoning task to test this transformation reasoning ability in real-world scenarios, called Visual Transformation Telling (VTT). Given a series of states (i.e. images), VTT requires to describe the transformation occurring between every two adjacent states. Different from existing visual reasoning tasks that focus on surface state reasoning, the advantage of VTT is that it captures the underlying causes, e.g. actions or events, behind the differences among states. We collect a novel dataset to support the study of transformation reasoning from two existing instructional video datasets, CrossTask and COIN, comprising 13,547 samples. Each sample involves the key state images along with their transformation descriptions. Our dataset covers diverse real-world activities, providing a rich resource for training and evaluation. To construct an initial benchmark for VTT, we test several models, including traditional visual storytelling methods (CST, GLACNet, Densecap) and advanced multimodal large language models (LLaVA v1.5-7B, Qwen-VL-chat, Gemini Pro Vision, GPT-4o, and GPT-4). Experimental results reveal that even state-of-the-art models still face challenges in VTT, highlighting substantial areas for improvement. © 2023, CC BY-NC-SA.

关键词： Visual languages

Edge Resource Prediction and Auction for Distributed Spatial Crowdsourcing With Differential Privacy

学校读者我要写书评

暂无评论

Edge Resource Prediction and Auction for Distributed Spatial...

作者： Xu, Yin Xiao, Mingjun Liu, An Wu, Jie Suzhou Institute for Advanced Research The Cas Key Laboratory of Wireless-Optical Communications University of Science and Technology of China School of Computer Science and Technology Hefei230026 China Soochow University School of Computer Science and Technology Suzhou215006 China Temple University Center for Networked Computing PhiladelphiaPA19122 United States

Traditional spatial crowdsourcing (SC) systems employ a centralized server platform to provide services for requesters. Such a centralized design requires powerful resource capacity and often cannot accomplish the urgent demands due to the unpredictable network latency. In order to ensure the scalability of systems and the quality of services, we study the distributed SC (DSC), where a diversity of location-relative services provided by various service providers (SPs) can deploy on edge clouds (ECs) with low time latency. Since the edge resources are limited, SPs need to compete for edge resources so as to deploy their desired SC services, and the requested resources must be allocated together to meet the demand of the service. We first design a gated recurrent unit with particle filter (GRUPF) network for SPs to predict future resource demands so as to participate in the competitions judiciously. Then, we model the competitive edge resource allocation problem between SPs and ECs as a combinatorial auction process. Due to the NP-hardness of this problem, an approximation algorithm is proposed to tackle it. Moreover, the leakage of private information such as bids may incur severe economic damage, and most existing studies usually rely on a trusted third party to provide rigorous privacy protection. Therefore, we customize a novel differentially private resource auction (DRA) mechanism, and design a bid confusion strategy based on differential privacy. Through theoretical analysis, we prove that the DRA mechanism meets some desired properties, including ϵ-differential privacy, individual rationality, computational efficiency, and γ-truthfulness. Additionally, we corroborate the significant performances of DRA through extensive simulations on synthetic and real-world data sets. © 2014 IEEE.

关键词： Internet of things

Slimmable generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hou, Liang Yuan, Zehuan Huang, Lei Shen, Huawei Cheng, Xueqi Wang, Changhu CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences ByteDance AI Lab SKLSDE Institute of Artificial Intelligence Beihang University

Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes them challenging to deploy widely in practical applications. In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power. In this paper, we introduce slimmable GANs (SlimGANs), which can flexibly switch the width of the generator to accommodate various quality-efficiency trade-offs at runtime. Specifically, we leverage multiple discriminators that share partial parameters to train the slimmable generator. To facilitate the consistency between generators of different widths, we present a stepwise inplace distillation technique that encourages narrow generators to learn from wide ones. As for class-conditional generation, we propose a sliceable conditional batch normalization that incorporates the label information into different widths. Our methods are validated, both quantitatively and qualitatively, by extensive experiments and a detailed ablation study. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ma, Xinyu Guo, Jiafeng Zhang, Ruqing Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Dense retrieval has shown promising results in many information retrieval (IR) related tasks, whose foundation is high-quality text representation learning for effective search. Some recent studies have shown that autoencoder-based language models are able to boost the dense retrieval performance using a weak decoder. However, we argue that 1) it is not discriminative to decode all the input texts and, 2) even a weak decoder has the bypass effect on the encoder. Therefore, in this work, we introduce a novel contrastive span prediction task to pre-train the encoder alone, but still retain the bottleneck ability of the autoencoder. The key idea is to force the encoder to generate the text representation close to its own random spans while far away from others using a group-wise contrastive loss. In this way, we can 1) learn discriminative text representations efficiently with the group-wise contrastive learning over spans and, 2) avoid the bypass effect of the decoder thoroughly. Comprehensive experiments over publicly available retrieval benchmark datasets show that our approach can outperform existing pre-training methods for dense retrieval significantly. Code and pre-trained models will be available at the URL. Copyright © 2022, The Authors. All rights reserved.

关键词： Signal encoding

Uncertainty calibration for ensemble-based debiasing methods 21

学校读者我要写书评

暂无评论

Uncertainty calibration for ensemble-based debiasing methods

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Ruibin Xiong Yimeng Chen Liang Pang Xueqi Cheng Zhiming Ma Yanyan Lan CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences and Baidu Inc. University of Chinese Academy of Sciences and Academy of Mathematics and Systems Science Chinese Academy of Sciences University of Chinese Academy of Sciences and Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Institute for AI Industry Research Tsinghua University

ISBN: (纸本)9781713845393

Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adjust the learning target. In this paper, we focus on the bias-only model in these ensemble-based methods, which plays an important role but has not gained much attention in the existing literature. Theoretically, we prove that the debiasing performance can be damaged by inaccurate uncertainty estimations of the bias-only model. Empirically, we show that existing bias-only models fall short in producing accurate uncertainty estimations. Motivated by these findings, we propose to conduct calibration on the bias-only model, thus achieving a three-stage ensemble-based debiasing framework, including bias modeling, model calibrating, and debiasing. Experimental results on NLI and fact verification tasks show that our proposed three-stage debiasing framework consistently outperforms the traditional two-stage one in out-of-distribution accuracy.

关键词：

Learning to truncate ranked lists for information retrieval

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Chen Zhang, Ruqing Guo, Jiafeng Fan, Yixing Lan, Yanyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Ranked list truncation is of critical importance in a variety of professional information retrieval applications such as patent search or legal search. The goal is to dynamically determine the number of returned documents according to some user-defined objectives, in order to reach a balance between the overall utility of the results and user efforts. Existing methods formulate this task as a sequential decision problem and take some pre-defined loss as a proxy objective, which suffers from the limitation of local decision and non-direct optimization. In this work, we propose a global decision based truncation model named AttnCut, which directly optimizes user-defined objectives for the ranked list truncation. Specifically, we take the successful transformer architecture to capture the global dependency within the ranked list for truncation decision, and employ the reward augmented maximum likelihood (RAML) for direct optimization. We consider two types of user-defined objectives which are of practical usage. One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search. Empirical results over the Robust04 and MQ2007 datasets demonstrate the effectiveness of our approach as compared with the state-of-the-art baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Information retrieval

Query understanding via intent description generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Ruqing Guo, Jiafeng Fan, Yixing Lan, Yanyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Query understanding is a fundamental problem in information retrieval (IR), which has attracted continuous attention through the past decades. Many different tasks have been proposed for understanding users’ search queries, e.g., query classification or query clustering. However, it is not that precise to understand a search query at the intent class/cluster level due to the loss of many detailed information. As we may find in many benchmark datasets, e.g., TREC and SemEval, queries are often associated with a detailed description provided by human annotators which clearly describes its intent to help evaluate the relevance of the documents. If a system could automatically generate a detailed and precise intent description for a search query, like human annotators, that would indicate much better query understanding has been achieved. In this paper, therefore, we propose a novel Query-to-Intent-Description (Q2ID) task for query understanding. Unlike those existing ranking tasks which leverage the query and its description to compute the relevance of documents, Q2ID is a reverse task which aims to generate a natural language intent description based on both relevant and irrelevant documents of a given query. To address this new task, we propose a novel Contrastive Generation model, namely CtrsGen for short, to generate the intent description by contrasting the relevant documents with the irrelevant documents given a query. We demonstrate the effectiveness of our model by comparing with several state-of-the-art generation models on the Q2ID task. We discuss the potential usage of such Q2ID technique through an example application. Copyright © 2020, The Authors. All rights reserved.

关键词：

LegoNet: A Fast and Exact Unlearning Architecture

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yu, Sihao Sun, Fei Guo, Jiafeng Zhang, Ruqing Cheng, Xueqi University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Machine unlearning aims to erase the impact of specific training samples upon deleted requests from a trained model. Retraining the model on the retained data after deletion is an effective but not efficient way due to the huge number of model parameters and re-training samples. To speed up, a natural way is to reduce such parameters and samples. However, such a strategy typically leads to a loss in model performance, which poses the challenge that increasing the unlearning efficiency while maintaining acceptable performance. In this paper, we present a novel network, namely LegoNet, which adopts the framework of "fixed encoder + multiple adapters". We fix the encoder (i.e., the backbone for representation learning) of LegoNet to reduce the parameters that need to be re-trained during unlearning. Since the encoder occupies a major part of the model parameters, the unlearning efficiency is significantly improved. However, fixing the encoder empirically leads to a significant performance drop. To compensate for the performance loss, we adopt the ensemble of multiple adapters, which are independent sub-models adopted to infer the prediction by the encoding (i.e., the output of the encoder). Furthermore, we design an activation mechanism for the adapters to further trade off unlearning efficiency against model performance. This mechanism guarantees that each sample can only impact very few adapters, so during unlearning, parameters and samples that need to be re-trained are both reduced. The empirical experiments verify that LegoNet accomplishes fast and exact unlearning while maintaining acceptable performance, synthetically outperforming unlearning baselines. © 2022, CC BY-NC-ND.

关键词： Efficiency

Controlling risk of web question answering

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Su, Lixin Guo, Jiafeng Fan, Yixing Lan, Yanyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Web question answering (QA) has become an indispensable component in modern search systems, which can significantly improve users’ search experience by providing a direct answer to users’ information need. This could be achieved by applying machine reading comprehension (MRC) models over the retrieved passages to extract answers with respect to the search query. With the development of deep learning techniques, state-of-the-art MRC performances have been achieved by recent deep methods. However, existing studies on MRC seldom address the predictive uncertainty issue, i.e., how likely the prediction of an MRC model is wrong, leading to uncontrollable risks in real-world Web QA applications. In this work, we first conduct an in-depth investigation over the risk of Web QA. We then introduce a novel risk control framework, which consists of a qualify model for uncertainty estimation using the probe idea, and a decision model for selectively output. For evaluation, we introduce risk-related metrics, rather than the traditional EM and F1 in MRC, for the evaluation of risk-aware Web QA. The empirical results over both the real-world Web QA dataset and the academic MRC benchmark collection demonstrate the effectiveness of our approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning