Differentiable Search Indices (DSIs) encode a corpus of documents in the parameters of a model and use the same model to map queries directly to relevant document identifiers. Despite the strong performance of DSI models, deploying them in situations where the corpus changes over time is computationally expensive because reindexing the corpus requires re-training the model. In this work, we introduce DSI++, a continual learning challenge for DSI to incrementally index new documents while being able to answer queries related to both previously and newly indexed documents. Across different model scales and document identifier representations, we show that continual indexing of new documents leads to considerable forgetting of previously indexed documents. We also hypothesize and verify that the model experiences forgetting events during training, leading to unstable learning. To mitigate these issues, we investigate two approaches. The first focuses on modifying the training dynamics. Flatter minima implicitly alleviate forgetting, so we optimize for flatter loss basins and show that the model stably memorizes more documents (+12\%). Next, we introduce a generative memory to sample pseudo-queries for documents and supplement them during continual indexing to prevent forgetting for the retrieval task. Extensive experiments on novel continual indexing benchmarks based on Natural Questions (NQ) and MS MARCO demonstrate that our proposed solution mitigates forgetting by a significant margin. Concretely, it improves the average Hits@10 by $+21.1\%$ over competitive baselines for NQ and requires $6$ times fewer model updates compared to re-training the DSI model for incrementally indexing five corpora in a sequence.
translated by 谷歌翻译
机器学习中的终身学习范式是一个有吸引力的替代方案,不仅是由于其与生物学学习的相似之处,而且它通过避免过度模型重新训练来减少能量浪费的可能性。对此范式的关键挑战是灾难性遗忘的现象。随着在机器学习中训练有素的模型的越来越受欢迎和成功,我们提出了问题:终身学习中的训练前比赛,特别是关于灾难性的遗忘?我们在大型预先训练模型的上下文中调查现有方法,并在各种文本和图像分类任务中评估其性能,包括使用15个不同的NLP任务的新型数据集进行大规模研究。在所有设置中,我们观察到,通用预训练隐含地减轻了在与随机初始化模型相比依次学习多个任务时灾难性忘记的影响。然后,我们进一步调查为什么预先训练缓解在这个环境中忘记。我们通过分析损失景观来研究这种现象,发现预先训练的重量似乎可以通过导致更宽的最小值来缓解遗忘。基于这一洞察力,我们提出了对当前任务损失和损失盆地锐利的共同优化,以便在连续微调期间明确鼓励更广泛的盆地。我们表明,这种优化方法导致与跨多个设置的任务顺序持续学习的性能相当,而无需保留具有任务数量的大小的内存。
translated by 谷歌翻译
大型语言模型在各种任务上显示出令人印象深刻的几次结果。但是,当知识是此类结果的关键时,就像问题回答和事实检查之类的任务一样,似乎需要存储知识的大量参数计数。众所周知,检索增强模型可以在不需要多个参数的情况下在知识密集的任务上表现出色,但是目前尚不清楚它们是否在几个弹药设置中工作。在这项工作中,我们介绍了地图集,这是一个经过精心设计和预先训练的增强语言模型,能够通过很少的培训示例学习知识密集型任务。我们对包括MMLU,苏格兰短裙和归类等各种任务进行评估,并研究文档索引内容的影响,表明它可以很容易地进行更新。值得注意的是,在自然问题上仅使用64个示例在自然问题上达到超过42 \%的准确性,尽管参数少了50倍,但比540B参数模型的表现优于540b参数模型。
translated by 谷歌翻译
已经表明,在一个域上训练的双编码器经常概括到其他域以获取检索任务。一种广泛的信念是,一个双编码器的瓶颈层,其中最终得分仅仅是查询向量和通道向量之间的点产品,它过于局限,使得双编码器是用于域外概括的有效检索模型。在本文中,我们通过缩放双编码器模型的大小{\ em同时保持固定的瓶颈嵌入尺寸固定的瓶颈的大小来挑战这一信念。令人惊讶的是,令人惊讶的是,缩放模型尺寸会对各种缩放提高检索任务,特别是对于域外泛化。实验结果表明,我们的双编码器,\ textbf {g} enovalizable \ textbf {t} eTrievers(gtr),优先级%colbert〜\ cite {khattab2020colbertt}和现有的稀疏和密集的索取Beir DataSet〜\ Cite {Thakur2021Beir}显着显着。最令人惊讶的是,我们的消融研究发现,GTR是非常数据的高效,因为它只需要10 \%MARCO监督数据,以实现最佳域的性能。所有GTR模型都在https://tfhub.dev/google/collections/gtr/1发布。
translated by 谷歌翻译
Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as it would allow us to build truly intelligent systems showing stability and plasticity. Secondly, it would allow us to overcome the onerous limitation of retraining these architectures from scratch with the new updated data. In this thesis, we tackle the problem from multiple directions. In a first study, we show that in rehearsal-based techniques (systems that use memory buffer), the quantity of data stored in the rehearsal buffer is a more important factor over the quality of the data. Secondly, we propose one of the early works of incremental learning on ViTs architectures, comparing functional, weight and attention regularization approaches and propose effective novel a novel asymmetric loss. At the end we conclude with a study on pretraining and how it affects the performance in Continual Learning, raising some questions about the effective progression of the field. We then conclude with some future directions and closing remarks.
translated by 谷歌翻译
随着时间的流逝,不断扩大知识并利用其快速推广到新任务的能力是人类语言智能的关键特征。然而,现有对新任务进行快速概括的模型(例如,很少的学习方法)主要是在固定数据集中的单个镜头中训练,无法动态扩展其知识;虽然不断学习算法并非专门设计用于快速概括。我们提出了一种新的学习设置,对几杆学习者(CLIF)的持续学习,以应对统一设置的两个学习设置的挑战。 CLIF假设模型从依次到达的一系列不同的NLP任务中学习,从而积累了知识,以改善对新任务的概括,同时还保留了较早所学的任务的性能。我们研究了在持续学习设置中如何影响概括能力,评估许多持续学习算法,并提出一种新型的正则适配器生成方法。我们发现,灾难性的遗忘影响着概括能力的程度远低于所见任务的表现。虽然持续学习算法仍然可以为概括能力带来可观的好处。
translated by 谷歌翻译
我们探索无任务持续学习(CL),其中培训模型以避免在没有明确的任务边界或身份的情况下造成灾难性的遗忘。在无任务CL上的许多努力中,一个值得注意的方法是基于内存的,存储和重放训练示例的子集。然而,由于CL模型不断更新,所以存储的示例的效用可以随时间缩短。这里,我们提出基于梯度的存储器编辑(GMED),该框架是通过梯度更新在连续输入空间中编辑存储的示例的框架,以便为重放创建更多的“具有挑战性”示例。 GMED编辑的例子仍然类似于其未编辑的形式,但可以在即将到来的模型更新中产生增加的损失,从而使未来的重播在克服灾难性遗忘方面更有效。通过施工,GMED可以与其他基于内存的CL算法一起无缝应用,以进一步改进。实验验证了GMED的有效性,以及我们最好的方法显着优于基线和以前的五个数据集中的最先进。可以在https://github.com/ink-usc/gmed找到代码。
translated by 谷歌翻译
可区分的搜索索引(DSI)是一个新的新兴范式,用于信息检索。与索引和检索是两个不同且独立的组件的传统检索体系结构不同,DSI使用单个变压器模型执行索引和检索。在本文中,我们确定并解决了当前DSI模型的重要问题:DSI索引和检索过程之间发生的数据分布不匹配。具体而言,我们认为,在索引时,当前的DSI方法学会学会在长文档文本及其标识之间建立连接,但是在检索中,向DSI模型提供了简短的查询文本以执行文档标识符的检索。当使用DSI进行跨语言检索时,此问题进一步加剧,其中文档文本和查询文本使用不同的语言。为了解决当前DSI模型的这个基本问题,我们为DSI称为DSI-QG的简单而有效的索引框架。在DSI-QG中,文档由索引时间的查询生成模型生成的许多相关查询表示。这允许DSI模型在索引时将文档标识符连接到一组查询文本,因此减轻索引和检索阶段之间存在的数据分布不匹配。流行的单语言和跨语性通过基准数据集的经验结果表明,DSI-QG明显优于原始DSI模型。
translated by 谷歌翻译
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual semi-supervised learning -- a setting where not all the data samples are labeled. An underlying issue in this scenario is the model forgetting representations of unlabeled data and overfitting the labeled ones. We leverage the power of nearest-neighbor classifiers to non-linearly partition the feature space and learn a strong representation for the current task, as well as distill relevant information from previous tasks. We perform a thorough experimental evaluation and show that our method outperforms all the existing approaches by large margins, setting a strong state of the art on the continual semi-supervised learning paradigm. For example, on CIFAR100 we surpass several others even when using at least 30 times less supervision (0.8% vs. 25% of annotations).
translated by 谷歌翻译
持续学习背后的主流范例一直在使模型参数调整到非静止数据分布,灾难性遗忘是中央挑战。典型方法在测试时间依赖排练缓冲区或已知的任务标识,以检索学到的知识和地址遗忘,而这项工作呈现了一个新的范例,用于持续学习,旨在训练更加简洁的内存系统而不在测试时间访问任务标识。我们的方法学会动态提示(L2P)预先训练的模型,以在不同的任务转换下顺序地学习任务。在我们提出的框架中,提示是小型可学习参数,这些参数在内存空间中保持。目标是优化提示,以指示模型预测并明确地管理任务不变和任务特定知识,同时保持模型可塑性。我们在流行的图像分类基准下进行全面的实验,具有不同挑战的持续学习环境,其中L2P始终如一地优于现有最先进的方法。令人惊讶的是,即使没有排练缓冲区,L2P即使没有排练缓冲,L2P也能实现竞争力的结果,并直接适用于具有挑战性的任务不可行的持续学习。源代码在https://github.com/google-Research/l2p中获得。
translated by 谷歌翻译
Question Generation (QG), as a challenging Natural Language Processing task, aims at generating questions based on given answers and context. Existing QG methods mainly focus on building or training models for specific QG datasets. These works are subject to two major limitations: (1) They are dedicated to specific QG formats (e.g., answer-extraction or multi-choice QG), therefore, if we want to address a new format of QG, a re-design of the QG model is required. (2) Optimal performance is only achieved on the dataset they were just trained on. As a result, we have to train and keep various QG models for different QG datasets, which is resource-intensive and ungeneralizable. To solve the problems, we propose a model named Unified-QG based on lifelong learning techniques, which can continually learn QG tasks across different datasets and formats. Specifically, we first build a format-convert encoding to transform different kinds of QG formats into a unified representation. Then, a method named \emph{STRIDER} (\emph{S}imilari\emph{T}y \emph{R}egular\emph{I}zed \emph{D}ifficult \emph{E}xample \emph{R}eplay) is built to alleviate catastrophic forgetting in continual QG learning. Extensive experiments were conducted on $8$ QG datasets across $4$ QG formats (answer-extraction, answer-abstraction, multi-choice, and boolean QG) to demonstrate the effectiveness of our approach. Experimental results demonstrate that our Unified-QG can effectively and continually adapt to QG tasks when datasets and formats vary. In addition, we verify the ability of a single trained Unified-QG model in improving $8$ Question Answering (QA) systems' performance through generating synthetic QA data.
translated by 谷歌翻译
Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limited, and hence on knowledge-intensive tasks, their performance lags behind task-specific architectures. Additionally, providing provenance for their decisions and updating their world knowledge remain open research problems. Pre-trained models with a differentiable access mechanism to explicit nonparametric memory can overcome this issue, but have so far been only investigated for extractive downstream tasks. We explore a general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -models which combine pre-trained parametric and non-parametric memory for language generation. We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. We compare two RAG formulations, one which conditions on the same retrieved passages across the whole generated sequence, and another which can use different passages per token. We fine-tune and evaluate our models on a wide range of knowledge-intensive NLP tasks and set the state of the art on three open domain QA tasks, outperforming parametric seq2seq models and task-specific retrieve-and-extract architectures. For language generation tasks, we find that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline.
translated by 谷歌翻译
在信息检索(IR)系统中,趋势和用户的兴趣可能会随着时间的推移而变化,改变要建议的请求或内容的分布。由于神经排名越来越依赖于培训数据,因此了解最近IR方法的转移能力在长期地址新域名的转移能力至关重要。在本文中,我们首先提出基于MSMarco语料库的数据集,旨在建模长期的主题以及IR属性驱动的受控设置。然后,我们深入分析最近神经红外模型的能力,同时不断地学习这些流。我们的实证研究突出显示在其中发生灾难性遗忘(例如,任务之间的相似程度,文本长度的特点,学习模型的方式),以便在模型设计方面提供未来的方向。
translated by 谷歌翻译
持续学习旨在快速,不断地从一系列任务中学习当前的任务。与其他类型的方法相比,基于经验重播的方法表现出了极大的优势来克服灾难性的遗忘。该方法的一个常见局限性是上一个任务和当前任务之间的数据不平衡,这将进一步加剧遗忘。此外,如何在这种情况下有效解决稳定性困境也是一个紧迫的问题。在本文中,我们通过提出一个通过多尺度知识蒸馏和数据扩展(MMKDDA)提出一个名为Meta学习更新的新框架来克服这些挑战。具体而言,我们应用多尺度知识蒸馏来掌握不同特征级别的远程和短期空间关系的演变,以减轻数据不平衡问题。此外,我们的方法在在线持续训练程序中混合了来自情节记忆和当前任务的样品,从而减轻了由于概率分布的变化而减轻了侧面影响。此外,我们通过元学习更新来优化我们的模型,该更新诉诸于前面所看到的任务数量,这有助于保持稳定性和可塑性之间的更好平衡。最后,我们对四个基准数据集的实验评估显示了提出的MMKDDA框架对其他流行基线的有效性,并且还进行了消融研究,以进一步分析每个组件在我们的框架中的作用。
translated by 谷歌翻译
经过审计的语言模型(PTLMS)通常是通过大型静态语料库学习的,并针对各种下游任务进行了微调。但是,当部署在现实世界中时,基于PTLM的模型必须处理偏离PTLM最初培训的数据分布。在本文中,我们研究了一个终身语言模型预处理挑战,其中不断更新PTLM以适应新兴数据。在域内收入的研究纸流和按时间顺序排序的推文流上,我们从具有不同持续学习算法的PTLM逐渐预处理PTLM,并跟踪下游任务性能(经过微调之后)。我们评估了PTLM在保留早期语料库中学习知识的同时适应新语料库的能力。我们的实验表明,基于蒸馏的方法最有效地在早期域中保持下游性能。该算法还可以改善知识传递,从而使模型能够比最新数据实现更好的下游性能,并在由于时间而在培训和评估之间存在分配差距时改善时间概括。我们认为,我们的问题制定,方法和分析将激发未来的研究朝着语言模型的持续预处理。
translated by 谷歌翻译
关于信息检索的许多最新研究集中在如何从一项任务(通常具有丰富的监督数据)转移到有限的其他各种任务,并隐含地假设可以从一个任务概括到所有其余的任务。但是,这忽略了这样一个事实,即有许多多样化和独特的检索任务,每个任务都针对不同的搜索意图,查询和搜索域。在本文中,我们建议使用几乎没有散热的检索,每个任务都有一个简短的描述和一些示例。为了扩大一些示例的功能,我们提出了针对检索器(即将到来)的及时基本查询生成,该查询将大型语言模型(LLM)作为几个弹片查询生成器,并根据生成的数据创建特定于任务的检索器。通过LLM的概括能力提供动力,即要来源使得可以仅基于一些示例{没有自然问题或MS MARCO来训练%问题生成器或双重编码器,就可以仅基于一些示例{没有}来创建特定于任务的端到端检索。出乎意料的是,LLM提示不超过8个示例,允许双重编码器在MARCO(例如Colbert V2)上训练的大量工程模型平均在11个检索套件中超过1.2 NDCG。使用相同生成数据的进一步培训标准尺寸的重新级别可获得5.0点NDCG的改进。我们的研究确定,查询产生比以前观察到的更有效,尤其是在给出少量特定于任务知识的情况下。
translated by 谷歌翻译
根据互补学习系统(CLS)理论〜\ cite {mcclelland1995there}在神经科学中,人类通过两个补充系统有效\ emph {持续学习}:一种快速学习系统,以海马为中心,用于海马,以快速学习细节,个人体验,个人体验,个人体验,个人体验,个人体验,个人体验,个人体验,个人体验的快速学习, ;以及位于新皮层中的缓慢学习系统,以逐步获取有关环境的结构化知识。在该理论的激励下,我们提出\ emph {dualnets}(对于双网络),这是一个一般的持续学习框架,该框架包括一个快速学习系统,用于监督从特定任务和慢速学习系统中的模式分离代表学习,用于表示任务的慢学习系统 - 不可知论的一般代表通过自我监督学习(SSL)。双网符可以无缝地将两种表示类型纳入整体框架中,以促进在深层神经网络中更好地持续学习。通过广泛的实验,我们在各种持续的学习协议上展示了双网络的有希望的结果,从标准离线,任务感知设置到具有挑战性的在线,无任务的场景。值得注意的是,在Ctrl〜 \ Cite {veniat2020202020202020202020202020202020202020202020202020202020202021- coite {ostapenko2021-continual}的基准中。此外,我们进行了全面的消融研究,以验证双nets功效,鲁棒性和可伸缩性。代码可在\ url {https://github.com/phquang/dualnet}上公开获得。
translated by 谷歌翻译
从头开始解决复杂问题通常是有挑战性的,但如果我们可以访问其解决方案的其他类似问题,则更容易 - 一种称为基于案例的推理(CBR)的范式。我们提出了一种神经象征性的CBR方法(CBR-KBQA),用于在大知识库上应答。 CBR-KBQA由非参数内存组成,该内存存储案例(问题和逻辑表单)和参数模型,该参数模型可以通过检索与其相关的案例来为新问题生成逻辑表单。在包含复杂问题的几个KBQA数据集上,CBR-KBQA实现了竞争性能。例如,在ComplexWebQuestions数据集上,CBR-KBQA以11 \%的准确度优于当前最新状态。此外,我们表明CBR-KBQA能够使用新案例\ EMPH {没有}任何进一步的培训:通过在案例存储器中纳入一些人类标记的示例,CBR-KBQA能够成功地生成包含未经看线KB实体的逻辑表格以及关系。
translated by 谷歌翻译
Modern machine learning pipelines are limited due to data availability, storage quotas, privacy regulations, and expensive annotation processes. These constraints make it difficult or impossible to maintain a large-scale model trained on growing annotation sets. Continual learning directly approaches this problem, with the ultimate goal of devising methods where a neural network effectively learns relevant patterns for new (unseen) classes without significantly altering its performance on previously learned ones. In this paper, we address the problem of continual learning for video data. We introduce PIVOT, a novel method that leverages the extensive knowledge in pre-trained models from the image domain, thereby reducing the number of trainable parameters and the associated forgetting. Unlike previous methods, ours is the first approach that effectively uses prompting mechanisms for continual learning without any in-domain pre-training. Our experiments show that PIVOT improves state-of-the-art methods by a significant 27% on the 20-task ActivityNet setup.
translated by 谷歌翻译
持续学习研究的主要重点领域是通过设计新算法对分布变化更强大的新算法来减轻神经网络中的“灾难性遗忘”问题。尽管持续学习文献的最新进展令人鼓舞,但我们对神经网络的特性有助于灾难性遗忘的理解仍然有限。为了解决这个问题,我们不关注持续的学习算法,而是在这项工作中专注于模型本身,并研究神经网络体系结构对灾难性遗忘的“宽度”的影响,并表明宽度在遗忘遗产方面具有出人意料的显着影响。为了解释这种效果,我们从各个角度研究网络的学习动力学,例如梯度正交性,稀疏性和懒惰的培训制度。我们提供了与不同架构和持续学习基准之间的经验结果一致的潜在解释。
translated by 谷歌翻译