检索结果-内蒙古大学图书馆

10th International Conference on Learning Representations, ICLR 2022

作者： Su, Bing Wen, Ji-Rong Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China

Explainable distances for sequence data depend on temporal alignment to tackle sequences with different lengths and local variances. Most sequence alignment methods infer the optimal alignment by solving an optimization problem under pre-defined feasible alignment constraints, which not only is time-consuming, but also makes end-to-end sequence learning intractable. In this paper, we propose a learnable sequence distance called Temporal Alignment Prediction (TAP). TAP employs a lightweight convolutional neural network to directly predict the optimal alignment between two sequences, so that only straightforward calculations are required and no optimization is involved in inference. TAP can be applied in different distance-based machine learning tasks. For supervised sequence representation learning, we show that TAP trained with various metric learning losses achieves completive performances with much faster inference speed. For few-shot action classification, we apply TAP as the distance measure in the metric learning-based episode-training paradigm. This simple strategy achieves comparable results with state-of-the-art few-shot action recognition methods. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References

Not All Metrics Are Guilty: Improving NLG Evaluation by Dive...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Tang, Tianyi Lu, Hongyuan Jiang, Yuchen Eleanor Huang, Haoyang Zhang, Dongdong Zhao, Wayne Xin Kocmi, Tom Wei, Furu Gaoling School of Artificial Intelligence Renmin University of China China Microsoft Research Asia China Microsoft China The Chinese University of Hong Kong Hong Kong AIWaves Inc Beijing Key Laboratory of Big Data Management and Analysis Methods China

ISBN: (纸本)9798891761148

Most research about natural language generation (NLG) relies on evaluation benchmarks with limited references for a sample, which may result in poor correlations with human judgements. The underlying reason is that one semantic meaning can actually be expressed in different forms, and the evaluation with a single or few references may not accurately reflect the quality of the model’s hypotheses. To address this issue, this paper presents a simple and effective method, named Div-Ref, to enhance existing evaluation benchmarks by enriching the number of references. We leverage large language models (LLMs) to diversify the expression of a single reference into multiple high-quality ones to cover the semantic space of the reference sentence as much as possible. We conduct comprehensive experiments to empirically demonstrate that diversifying the expression of reference can significantly enhance the correlation between automatic evaluation and human evaluation. This idea is compatible with recent LLM-based evaluation which can similarly derive advantages from incorporating multiple references. We strongly encourage future generation benchmarks to include more references, even if they are generated by LLMs, which is once for all. We release all the code and data at https://***/RUCAIBox/Div-Ref to facilitate research. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders 23

Learning Vector-Quantized Item Representation for Transferab...

引用

2023 World Wide Web Conference, WWW 2023

作者： Hou, Yupeng He, Zhankui McAuley, Julian Zhao, Wayne Xin Gaoling School of Artifcial Intelligence Renmin University of China Beijing China Uc San Diego San DiegoCA United States Beijing Key Laboratory of Big Data Management and Analysis Methods China

ISBN: (纸本)9781450394161

Recently, the generality of natural language text has been leveraged to develop transferable recommender systems. The basic idea is to employ pre-trained language models (PLM) to encode item text into item representations. Despite the promising transferability, the binding between item text and item representations might be too tight, leading to potential problems such as over-emphasizing the effect of text features and exaggerating the negative impact of domain gap. To address this issue, this paper proposes VQ-Rec, a novel approach to learning Vector-Quantized item representations for transferable sequential Recommenders. The main novelty of our approach lies in the new item representation scheme: it first maps item text into a vector of discrete indices (called item code), and then employs these indices to lookup the code embedding table for deriving item representations. Such a scheme can be denoted as "text ĝ code ĝ representation". Based on this representation scheme, we further propose an enhanced contrastive pre-training approach, using semi-synthetic and mixed-domain code representations as hard negatives. Furthermore, we design a new cross-domain fine-tuning method based on a differentiable permutation-based network. Extensive experiments conducted on six public benchmarks demonstrate the effectiveness of the proposed approach, in both cross-domain and cross-platform settings. Code and pre-trained model are available at: https://***/RUCAIBox/VQ-Rec. © 2023 ACM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Tuple Transfer for Pipelined Query Execution on CPU-GPU Coprocessor 28th

Fine-Grained Tuple Transfer for Pipelined Query Execution o...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Yang, Zhenhua Pan, Qingfeng Xu, Chen Shanghai Engineering Research Center of Big Data Management East China Normal University Shanghai200062 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9783031306365

To leverage the massively parallel capability of GPU for query execution, GPU databases have been studied for over a decade. Recently, researchers proposed to execute queries with both CPU and GPU in a pipelined approach. In the pipelined query execution, the cross-processor tuple transfer plays a crucial role for the overall query execution performance. The state-of-the-art solution achieves cross-processor tuple transfer using a queue-like data structure. However, it is coarse-grained due to the use of a single spin lock to achieve thread-safety. This design causes performance issues as it prevents the threads from accessing the queue simultaneously. In this paper, we propose a fine-grained tuple transfer mechanism. It employs decoupled enqueue/dequeue to enable two threads on different processors to access the queue at the same time. Moreover, this mechanism explores subqueue-based locking to enable the threads on the same processor to access the queue at the same time. In particular, we implement a prototype system, namely π QC, which adopts fine-grained tuple transfer. Our experiments show that π QC achieves an order of magnitude better performance than existing GPU databases such as HeavyDB. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Sequential Recommendation with User Causal Behavior Discovery 39

Sequential Recommendation with User Causal Behavior Discover...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Wang, Zhenlei Chen, Xu Zhou, Rui Dai, Quanyu Dong, Zhenhua Wen, Ji-Rong Renmin University of China Gaoling School of Artificial Intelligence Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Noah's Ark Lab Huawei Beijing China

ISBN: (纸本)9798350322279

The key of sequential recommendation lies in the accurate item correlation modeling. Previous models infer such information based on item co-occurrences, which may fail to capture the real causal relations, and impact the recommendation performance and explainability. In this paper, we equip sequential recommendation with a novel causal discovery module to capture causalities among user behaviors. Our general idea is firstly assuming a causal graph underlying item correlations, and then we learn the causal graph jointly with the sequential recommender model by fitting the real user behavior data. More specifically, in order to satisfy the causality requirement, the causal graph is regularized by a differentiable directed acyclic constraint. Considering that the number of items in recommender systems can be very large, we represent different items with a unified set of latent clusters, and the causal graph is defined on the cluster level, which enhances the model scalability and robustness. In addition, we provide theoretical analysis on the identifiability of the learned causal graph. To the best of our knowledge, this paper makes a first step towards combining sequential recommendation with causal discovery. For evaluating the recommendation performance, we implement our framework with different neural sequential architectures, and compare them with many state-of-the-art methods based on real-world datasets. Empirical studies manifest that our model can on average improve the performance by about 6.1% and 11.3% on F1 and NDCG, respectively. To evaluate the model explainability, we build a new dataset with human labeled explanations for both quantitative and qualitative analysis. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Generalized robust loss functions for machine learning

引用

NEURAL NETWORKS 2024年 171卷 200-214页

作者： Fu, Saiji Wang, Xiaoxiao Tang, Jingjing Lan, Shulin Tian, Yingjie Beijing Univ Posts & Telecommun Sch Econ & Management Beijing 100876 Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Southwestern Univ Finance & Econ Fac Business Adm Sch Business Adm Chengdu 611130 Peoples R China Southwestern Univ Finance & Econ Inst Big Data Chengdu 611130 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China UCAS MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China

Loss function is a critical component of machine learning. Some robust loss functions are proposed to mitigate the adverse effects caused by noise. However, they still face many challenges. Firstly, there is currently a lack of unified frameworks for building robust loss functions in machine learning. Secondly, most of them only care about the occurring noise and pay little attention to those normal points. Thirdly, the resulting performance gain is limited. To this end, we put forward a general framework of robust loss functions for machine learning (RML) with rigorous theoretical analyses, which can smoothly and adaptively flatten any unbounded loss function and apply to various machine learning problems. In RML, an unbounded loss function serves as the target, with the aim of being flattened. A scale parameter is utilized to limit the maximum value of noise points, while a shape parameter is introduced to control both the compactness and the growth rate of the flattened loss function. Later, this framework is employed to flatten the Hinge loss function and the Square loss function. Based on this, we build two robust kernel classifiers called FHSVM and FLSSVM, which can distinguish different types of data. The stochastic variance reduced gradient (SVRG) approach is used to optimize FHSVM and FLSSVM. Extensive experiments demonstrate their superiority, with both consistently occupying the top two positions among all evaluated methods, achieving an average accuracy of 81.07% (accompanied by an F-score of 73.25%) for FHSVM and 81.54% (with an F-score of 75.71%) for FLSSVM.

关键词： Robust loss function Machine learning Kernel classifier Flattened Squares loss function Flattened Hinge loss function

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques 38

Suppress Content Shift: Better Diffusion Features via Off-th...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs

arXiv

引用

arXiv 2024年

作者： Ji, Shengwei Tian, Yujie Liu, Fei Li, Xinlu Wu, Le The School of Artificial Intelligence and Big Data Hefei University Hefei China The School of Computer Science and Information Engineering Hefei University of Technology Hefei China The Key Laboratory of Knowledge Engineering with Big Data Ministry of Education China

Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out of memory (OOM) errors on mainstream GPUs (e.g., 29GB memory consumption on the Ogbn-products graph with 5 layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgraphs, i.e., GCNs can only be trained based on subgraphs instead of global graph information, which reduces the accuracy of GCNs. In this paper, we propose PromptGCN, a novel prompt-based lightweight GCN model to bridge the gaps among subgraphs. First, the learnable prompt embeddings are designed to obtain global information. Then, the prompts are attached into each subgraph to transfer the global information among subgraphs. Extensive experimental results on seven large-scale graphs demonstrate that PromptGCN exhibits superior performance compared to baselines. Notably, PromptGCN improves the accuracy of subgraph sampling methods by up to 5.48% on the Flickr dataset. Overall, PromptGCN can be easily combined with any subgraph sampling method to obtain a lightweight GCN model with higher accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection 39

Each Fake News is Fake in its Own Way: An Attribution Multi-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Hao Ma, Zihan Zeng, Zhi Luo, Minnan Zeng, Weixin Tang, Jiuyang Zhao, Xiang Laboratory for Big Data and Decision Nation University of Defense Technology China School of Computer Science and Technology Xi’an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China

ISBN: (纸本)157735897X

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset AMG, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model MGCA to achieve multimodal fake news detection and attribution. Experimental results demonstrate that AMG is a challenging dataset, and its attribution setting opens up new avenues for future research. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：