检索结果-内蒙古大学图书馆

Large language models are semi-parametric reinforcement learning agents 23

学校读者我要写书评

暂无评论

Large language models are semi-parametric reinforcement lear...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Danyang Zhang Lu Chen Situo Zhang Hongshen Xu Zihan Zhao Kai Yu X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China and Suzhou Laboratory Suzhou China

Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as REMEMBERER. By equipping the LLM with a long-term experience memory, REMEMBERER is capable of exploiting the experiences from the past episodes even for different task goals, which excels an LLM-based agent with fixed exemplars or equipped with a transient working memory. We further introduce Reinforcement Learning with Experience Memory (RLEM) to update the memory. Thus, the whole system can learn from the experiences of both success and failure, and evolve its capability without fine-tuning the parameters of the LLM. In this way, the proposed REMEMBERER constitutes a semi-parametric RL agent. Extensive experiments are conducted on two RL task sets to evaluate the proposed framework. The average results with different initialization and training sets exceed the prior SOTA by 4% and 2% for the success rate on two task sets and demonstrate the superiority and robustness of REMEMBERER. The codes are open-sourced at https://***/OpenDFM/Rememberer.

关键词：

ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hanchong Cao, Ruisheng Chen, Lu Xu, Hongshen Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China

Recently Large Language Models (LLMs) have been proven to have strong abilities in various domains and tasks. We study the problem of prompt designing in the text-to-SQL task and attempt to improve the LLMs' reasoning ability when generating SQL queries. Besides the trivial few-shot in-context learning setting, we design our chain-of-thought (CoT) prompt with a similar method to schema linking. We provide a method named ACT-SQL1 to automatically generate auto-CoT exemplars and thus the whole process doesn't need manual labeling. Our approach is cost-saving since we only use the LLMs' API call once when generating one SQL query. Furthermore, we extend our in-context learning method to the multi-turn text-to-SQL task. The experiment results show that the LLMs' performance can benefit from our ACT-SQL approach. Our approach achieves SOTA performance on the Spider dev set among existing in-context learning approaches. © 2023, CC BY-SA.

关键词： Learning systems

CODE-SWITCHING TEXT GENERATION AND INJECTION IN MANDARIN-ENGLISH ASR

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Haibin Hu, Yuxuan Qian, Yao Jin, Ma Liu, Linquan Liu, Shujie Shi, Yu Qian, Yanmin Lin, Edward Zeng, Michael MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University China Microsoft Corporation

Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of data. In this study, we investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T), in Mandarin-English code-switching speech recognition. We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces. Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models, i.e., 16% relative Token-based Error Rate (TER) reduction averaged on three evaluation sets, and the approach of tying speech and text latent spaces is superior to that of TTS conversion on the evaluation set which contains more homogeneous data with the training set. Copyright © 2023, The Authors. All rights reserved.

关键词： Transducers

PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhong, Ruizhe Ye, Junjie Tang, Zhentao Kai, Shixiong Yuan, Mingxuan Hao, Jianye Yan, Junchi Dept. of Computer Science and Engineering MoE Key Lab of AI Shanghai Jiao Tong University China Huawei Noah’s Ark Lab Canada College of Intelligence and Computing Tianjin University China

Pre-routing timing prediction has been recently studied for evaluating the quality of a candidate cell placement in chip design. It involves directly estimating the timing metrics for both pin-level (slack, slew) and edge-level (net delay, cell delay), without time-consuming routing. However, it often suffers from signal decay and error accumulation due to the long timing paths in large-scale industrial circuits. To address these challenges, we propose a two-stage approach. First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from circuit netlist. Second, we use a novel node updating scheme for message passing on GCN, following the topological sorting sequence of the learned graph embedding and circuit graph. This scheme residually models the local time delay between two adjacent pins in the updating sequence, and extracts the lookup table information inside each cell via a new attention mechanism. To handle large-scale circuits efficiently, we introduce an order preserving partition scheme that reduces memory consumption while maintaining the topological dep.ndencies. Experiments on 21 real world circuits achieve a new SOTA R2 of 0.93 for slack prediction, which is significantly surpasses 0.59 by previous SOTA method. Code will be available at: https://***/Thinklab-SJTU/EDA-ai. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Bei Qian, Yanmin The Auditory Cognition and Computational Acoustics Lab. The Department of Computer Science and Engineering The MoE Key Laboratory of Artifificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Recent speaker verification (SV) systems have shown a trend toward adopting deeper speaker embedding extractors. Although deeper and larger neural networks can significantly improve performance, their substantial memory requirements hinder training on consumer GPUs. In this paper, we explore a memory-efficient training strategy for deep speaker embedding learning in resource-constrained scenarios. Firstly, we conduct a systematic analysis of GPU memory allocation during SV system training. Empirical observations show that activations and optimizer states are the main sources of memory consumption. For activations, we design two types of reversible neural networks which eliminate the need to store intermediate activations during back-propagation, thereby significantly reducing memory usage without performance loss. For optimizer states, we introduce a dynamic quantization approach that replaces the original 32-bit floating-point values with a dynamic tree-based 8-bit data type. Experimental results on VoxCeleb demonstrate that the reversible variants of ResNets and DF-ResNets can perform training without the need to cache activations in GPU memory. In addition, the 8-bit versions of SGD and Adam save 75% of memory costs while maintaining performance compared to their 32-bit counterparts. Finally, a detailed comparison of memory usage and performance indicates that our proposed models achieve up to 16.2x memory savings, with nearly identical parameters and performance compared to the vanilla systems. In contrast to the previous need for multiple high-end GPUs such as the A100, we can effectively train deep speaker embedding extractors with just one or two consumer-level 2080Ti GPUs. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphics processing unit

A Birgat Model for Multi-Intent Spoken Language Understanding with Hierarchical Semantic Frames

学校读者我要写书评

暂无评论

A Birgat Model for Multi-Intent Spoken Language Understandin...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hongshen Xu Ruisheng Cao Su Zhu Sheng Jiang Hanchong Zhang Lu Chen Kai Yu Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Shanghai Jiao Tong University Shanghai China AISpeech Co. Ltd Suzhou China

Previous work on spoken language understanding (SLU) mainly focuses on single-intent settings, where each input utterance merely contains one user intent. This configuration significantly limits the surface form of user utterances and the capacity of output semantics. In this work, we firstly propose a Multi-Intent dataset which is collected from a realistic in-Vehicle dialogue System, called MIVS. The target semantic frame is organized in a 3-layer hierarchical structure to tackle the alignment and assignment problems in multi-intent cases. Accordingly, we devise a BiRGAT model to encode the hierarchy of ontology items, the backbone of which is a dual relational graph attention network. Coupled with the 3-way pointer-generator decoder, our method outperforms traditional sequence labeling and classification-based schemes by a large margin. Ablation study in transfer learning settings further uncovers the poor generalizability of current models in multi-intent cases.

关键词：

Diffusion-Based Generative Modeling With Discriminative Guidance for Streamable Speech Enhancement

学校读者我要写书评

暂无评论

Diffusion-Based Generative Modeling With Discriminative Guid...

IEEE Spoken Language Technology Workshop

作者： Chenda Li Samuele Cornell Shinji Watanabe Yanmin Qian Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Carnegie Mellon University USA

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

Diffusion-based generative models (DGMs) have recently attracted attention in speech enhancement (SE) research as previous works showed a remarkable generalization capability. However, DGMs are also computationally intensive, since they usually require many iterations in the reverse diffusion process (RDP), making them impractical for streaming SE systems. In this paper, we propose to use scores estimated from discriminative models in the first steps of the RDP. These discriminative-based scores require only one forward pass with the discriminative model for multiple RDP steps, thus greatly reducing computations. This approach also allows for performance improvements. We show that choosing an appropriate number of discriminative guidance steps can result in an overall model with better performance than generative and discriminative models. Furthermore, we propose a novel streamable time-domain generative model with an algorithmic latency of 50 ms, which has no significant performance degradation compared to offline models.

关键词： Degradation Computational modeling Conferences Diffusion processes Speech enhancement Time-domain analysis

Improving Anomalous Sound Detection Via Low-Rank Adaptation Fine-Tuning of Pre-Trained Audio Models

学校读者我要写书评

暂无评论

Improving Anomalous Sound Detection Via Low-Rank Adaptation ...

IEEE Spoken Language Technology Workshop

作者： Xinhu Zheng Anbai Jiang Bing Han Yanmin Qian Pingyi Fan Jia Liu Wei-Qiang Zhang Department of Electronic Engineering Tsinghua University Beijing China Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artifcial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

Anomalous Sound Detection (ASD) has gained significant interest through the application of various Artificial Intelligence (ai) technologies in industrial settings. Though possessing great potential, ASD systems can hardly be readily dep.oyed in real production sites due to the generalization problem, which is primarily caused by the difficulty of data collection and the complexity of environmental factors. This paper introduces a robust ASD model that leverages audio pre-trained models. Specifically, we fine-tune these models using machine operation data, employing SpecAug as a data augmentation strategy. Additionally, we investigate the impact of utilizing Low-Rank Adaptation (LoRA) tuning instead of full fine-tuning to address the problem of limited data for fine-tuning. Our experiments on the DCASE2023 Task 2 dataset establish a new benchmark of 77.75% on the evaluation set, with a significant improvement of 6.48% compared with previous state-of-the-art (SOTA) models, including top-tier traditional convolutional networks and speech pre-trained models, which demonstrates the effectiveness of audio pre-trained models with LoRA tuning. Ablation studies are also conducted to showcase the efficacy of the proposed scheme.

关键词： Adaptation models Production Data collection Data augmentation Harmonic analysis Data models Environmental factors Convolutional neural networks Artificial intelligence Tuning

NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Qitian Zhao, Wentao Li, Zenan Wipf, David Yan, Junchi Department of Computer Science and Engineering Shanghai Jiao Tong University China Amazon Web Service Shanghai AI Lab China MoE Key Lab of Artificial Intelligence China Shanghai AI Laboratory China

Graph neural networks have been extensively studied for learning with interconnected data. Despite this, recent evidence has revealed GNNs’ deficiencies related to over-squashing, heterophily, handling long-range dep.ndencies, edge incompleteness and particularly, the absence of graphs altogether. While a plausible solution is to learn new adaptive topology for message passing, issues concerning quadratic complexity hinder simultaneous guarantees for scalability and precision in large networks. In this paper, we introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes, as an important building block for a pioneering Transformer-style network for node classification on large graphs, dubbed as NODEFORMER. Specifically, the efficient computation is enabled by a kernerlized Gumbel-Softmax operator that reduces the algorithmic complexity to linearity w.r.t. node numbers for learning latent graph structures from large, potentially fully-connected graphs in a differentiable manner. We also provide accompanying theory as justification for our design. Extensive experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs (with up to 2M nodes) and graph-enhanced applications (e.g., image classification) where input graphs are missing. The codes are available at https://***/qitianwu/NodeFormer. © 2023, CC BY.

关键词： Message passing