2022-12-02 更新
Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning
Authors:Witold Sosnowski, Karolina Seweryn, Anna Wróblewska, Piotr Gawrysiak
This paper presents an analysis regarding an influence of the Distance Metric Learning (DML) loss functions on the supervised fine-tuning of the language models for classification tasks. We experimented with known datasets from SentEval Transfer Tasks. Our experiments show that applying the DML loss function can increase performance on downstream classification tasks of RoBERTa-large models in few-shot scenarios. Models fine-tuned with the use of SoftTriple loss can achieve better results than models with a standard categorical cross-entropy loss function by about 2.89 percentage points from 0.04 to 13.48 percentage points depending on the training dataset. Additionally, we accomplished a comprehensive analysis with explainability techniques to assess the models’ reliability and explain their results.
PDF
点此查看论文截图
PatchMix Augmentation to Identify Causal Features in Few-shot Learning
Authors:Chengming Xu, Chen Liu, Xinwei Sun, Siqian Yang, Yabiao Wang, Chengjie Wang, Yanwei Fu
The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great practical values in the real-world applications. Despite extensive previous efforts are made on few-shot learning tasks, we emphasize that most existing methods did not take into account the distributional shift caused by sample selection bias in the FSL scenario. Such a selection bias can induce spurious correlation between the semantic causal features, that are causally and semantically related to the class label, and the other non-causal features. Critically, the former ones should be invariant across changes in distributions, highly related to the classes of interest, and thus well generalizable to novel classes, while the latter ones are not stable to changes in the distribution. To resolve this problem, we propose a novel data augmentation strategy dubbed as PatchMix that can break this spurious dependency by replacing the patch-level information and supervision of the query images with random gallery images from different classes from the query ones. We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features. To further make these features to be discriminative enough for classification, we propose Correlation-guided Reconstruction (CGR) and Hardness-Aware module for instance discrimination and easier discrimination between similar classes. Moreover, such a framework can be adapted to the unsupervised FSL scenario.
PDF
点此查看论文截图
Revisiting Distance Metric Learning for Few-Shot Natural Language Classification
Authors:Witold Sosnowski, Anna Wróblewska, Karolina Seweryn, Piotr Gawrysiak
Distance Metric Learning (DML) has attracted much attention in image processing in recent years. This paper analyzes its impact on supervised fine-tuning language models for Natural Language Processing (NLP) classification tasks under few-shot learning settings. We investigated several DML loss functions in training RoBERTa language models on known SentEval Transfer Tasks datasets. We also analyzed the possibility of using proxy-based DML losses during model inference. Our systematic experiments have shown that under few-shot learning settings, particularly proxy-based DML losses can positively affect the fine-tuning and inference of a supervised language model. Models tuned with a combination of CCE (categorical cross-entropy loss) and ProxyAnchor Loss have, on average, the best performance and outperform models with only CCE by about 3.27 percentage points — up to 10.38 percentage points depending on the training dataset.
PDF
点此查看论文截图
AUG-FedPrompt: Practical Few-shot Federated NLP with Data-augmented Prompts
Authors:Dongqi Cai, Yaozong Wu, Haitao Yuan, Shangguang Wang, Felix Xiaozhu Lin, Mengwei Xu
Transformer-based pre-trained models have become the de-facto solution for NLP tasks. Fine-tuning such pre-trained models for downstream tasks often requires tremendous amount of data that is both private and labeled. However, in reality: 1) such private data cannot be collected and is distributed across mobile devices, and 2) well-curated labeled data is scarce. To tackle those issues, we first define a data generator for federated few-shot learning tasks, which encompasses the quantity and distribution of scarce labeled data in a realistic setting. Then we propose AUG-FedPrompt, a prompt-based federated learning algorithm that carefully annotates abundant unlabeled data for data augmentation. AUG-FedPrompt can perform on par with full-set fine-tuning with very few initial labeled data.
PDF Under review at ICASSP
点此查看论文截图
Geoclidean: Few-Shot Generalization in Euclidean Geometry
Authors:Joy Hsu, Jiajun Wu, Noah D. Goodman
Euclidean geometry is among the earliest forms of mathematical thinking. While the geometric primitives underlying its constructions, such as perfect lines and circles, do not often occur in the natural world, humans rarely struggle to perceive and reason with them. Will computer vision models trained on natural images show the same sensitivity to Euclidean geometry? Here we explore these questions by studying few-shot generalization in the universe of Euclidean geometry constructions. We introduce Geoclidean, a domain-specific language for Euclidean geometry, and use it to generate two datasets of geometric concept learning tasks for benchmarking generalization judgements of humans and machines. We find that humans are indeed sensitive to Euclidean geometry and generalize strongly from a few visual examples of a geometric concept. In contrast, low-level and high-level visual features from standard computer vision models pretrained on natural images do not support correct generalization. Thus Geoclidean represents a novel few-shot generalization benchmark for geometric concept learning, where the performance of humans and of AI models diverge. The Geoclidean framework and dataset are publicly available for download.
PDF To appear at NeurIPS 2022
点此查看论文截图
ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
Authors:Qi Zhu, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gašić, Minlie Huang
Diverse data formats and ontologies of task-oriented dialogue (TOD) datasets hinder us from developing general dialogue models that perform well on many datasets and studying knowledge transfer between datasets. To address this issue, we present ConvLab-3, a flexible dialogue system toolkit based on a unified TOD data format. In ConvLab-3, different datasets are transformed into one unified format and loaded by models in the same way. As a result, the cost of adapting a new model or dataset is significantly reduced. Compared to the previous releases of ConvLab (Lee et al., 2019b; Zhu et al., 2020b), ConvLab-3 allows developing dialogue systems with much more datasets and enhances the utility of the reinforcement learning (RL) toolkit for dialogue policies. To showcase the use of ConvLab-3 and inspire future work, we present a comprehensive study with various settings. We show the benefit of pre-training on other datasets for few-shot fine-tuning and RL, and encourage evaluating policy with diverse user simulators.
PDF
点此查看论文截图
TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning
Authors:Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, Yu-Gang Jiang
Given sufficient training data on the source domain, cross-domain few-shot learning (CD-FSL) aims at recognizing new classes with a small number of labeled examples on the target domain. The key to addressing CD-FSL is to narrow the domain gap and transferring knowledge of a network trained on the source domain to the target domain. To help knowledge transfer, this paper introduces an intermediate domain generated by mixing images in the source and the target domain. Specifically, to generate the optimal intermediate domain for different target data, we propose a novel target guided dynamic mixup (TGDM) framework that leverages the target data to guide the generation of mixed images via dynamic mixup. The proposed TGDM framework contains a Mixup-3T network for learning classifiers and a dynamic ratio generation network (DRGN) for learning the optimal mix ratio. To better transfer the knowledge, the proposed Mixup-3T network contains three branches with shared parameters for classifying classes in the source domain, target domain, and intermediate domain. To generate the optimal intermediate domain, the DRGN learns to generate an optimal mix ratio according to the performance on auxiliary target data. Then, the whole TGDM framework is trained via bi-level meta-learning so that TGDM can rectify itself to achieve optimal performance on target data. Extensive experimental results on several benchmark datasets verify the effectiveness of our method.
PDF accepted by ACM MM 2022
点此查看论文截图
RAFT: Rationale adaptor for few-shot abusive language detection
Authors:Punyajoy Saha, Divyanshu Sheth, Kushal Kedia, Binny Mathew, Animesh Mukherjee
Abusive language is a concerning problem in online social media. Past research on detecting abusive language covers different platforms, languages, demographies, etc. However, models trained using these datasets do not perform well in cross-domain evaluation settings. To overcome this, a common strategy is to use a few samples from the target domain to train models to get better performance in that domain (cross-domain few-shot training). However, this might cause the models to overfit the artefacts of those samples. A compelling solution could be to guide the models toward rationales, i.e., spans of text that justify the text’s label. This method has been found to improve model performance in the in-domain setting across various NLP tasks. In this paper, we propose RAFT (Rationale Adaptor for Few-shoT classification) for abusive language detection. We first build a multitask learning setup to jointly learn rationales, targets, and labels, and find a significant improvement of 6% macro F1 on the rationale detection task over training solely rationale classifiers. We introduce two rationale-integrated BERT-based architectures (the RAFT models) and evaluate our systems over five different abusive language datasets, finding that in the few-shot classification setting, RAFT-based models outperform baseline models by about 7% in macro F1 scores and perform competitively to models finetuned on other source domains. Furthermore, RAFT-based models outperform LIME/SHAP-based approaches in terms of plausibility and are close in performance in terms of faithfulness.
PDF 9 pages, 6 tables, 2 figures
点此查看论文截图
Data-driven Science and Machine Learning Methods in Laser-Plasma Physics
Authors:Andreas Döpp, Christoph Eberle, Sunny Howard, Faran Irshad, Jinpu Lin, Matthew Streeter
Laser-plasma physics has developed rapidly over the past few decades as lasers have become both more powerful and more widely available. Early experimental and numerical research in this field was dominated by single-shot experiments with limited parameter exploration. However, recent technological improvements make it possible to gather data for hundreds or thousands of different settings in both experiments and simulations. This has sparked interest in using advanced techniques from mathematics, statistics and computer science to deal with, and benefit from, big data. At the same time, sophisticated modeling techniques also provide new ways for researchers to deal effectively with situation where still only sparse data are available. This paper aims to present an overview of relevant machine learning methods with focus on applicability to laser-plasma physics and its important sub-fields of laser-plasma acceleration and inertial confinement fusion.
PDF
点此查看论文截图
Large Language Models are Few-Shot Clinical Information Extractors
Authors:Monica Agrawal, Stefan Hegselmann, Hunter Lang, Yoon Kim, David Sontag
A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes. However, roadblocks have included dataset shift from the general domain and a lack of public clinical corpora and annotations. In this work, we show that large language models, such as InstructGPT, perform well at zero- and few-shot information extraction from clinical text despite not being trained specifically for the clinical domain. Whereas text classification and generation performance have already been studied extensively in such models, here we additionally demonstrate how to leverage them to tackle a diverse set of NLP tasks which require more structured outputs, including span identification, token-level sequence classification, and relation extraction. Further, due to the dearth of available data to evaluate these systems, we introduce new datasets for benchmarking few-shot clinical information extraction based on a manual re-annotation of the CASI dataset for new tasks. On the clinical extraction tasks we studied, the GPT-3 systems significantly outperform existing zero- and few-shot baselines.
PDF Accepted as a long paper to The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)
点此查看论文截图
Towards True Lossless Sparse Communication in Multi-Agent Systems
Authors:Seth Karten, Mycal Tucker, Siva Kailas, Katia Sycara
Communication enables agents to cooperate to achieve their goals. Learning when to communicate, i.e., sparse (in time) communication, and whom to message is particularly important when bandwidth is limited. Recent work in learning sparse individualized communication, however, suffers from high variance during training, where decreasing communication comes at the cost of decreased reward, particularly in cooperative tasks. We use the information bottleneck to reframe sparsity as a representation learning problem, which we show naturally enables lossless sparse communication at lower budgets than prior art. In this paper, we propose a method for true lossless sparsity in communication via Information Maximizing Gated Sparse Multi-Agent Communication (IMGS-MAC). Our model uses two individualized regularization objectives, an information maximization autoencoder and sparse communication loss, to create informative and sparse communication. We evaluate the learned communication `language’ through direct causal analysis of messages in non-sparse runs to determine the range of lossless sparse budgets, which allow zero-shot sparsity, and the range of sparse budgets that will inquire a reward loss, which is minimized by our learned gating function with few-shot sparsity. To demonstrate the efficacy of our results, we experiment in cooperative multi-agent tasks where communication is essential for success. We evaluate our model with both continuous and discrete messages. We focus our analysis on a variety of ablations to show the effect of message representations, including their properties, and lossless performance of our model.
PDF 12 pages, 6 figures
点此查看论文截图
Evidential Conditional Neural Processes
Authors:Deep Shankar Pandey, Qi Yu
The Conditional Neural Process (CNP) family of models offer a promising direction to tackle few-shot problems by achieving better scalability and competitive predictive performance. However, the current CNP models only capture the overall uncertainty for the prediction made on a target data point. They lack a systematic fine-grained quantification on the distinct sources of uncertainty that are essential for model training and decision-making under the few-shot setting. We propose Evidential Conditional Neural Processes (ECNP), which replace the standard Gaussian distribution used by CNP with a much richer hierarchical Bayesian structure through evidential learning to achieve epistemic-aleatoric uncertainty decomposition. The evidential hierarchical structure also leads to a theoretically justified robustness over noisy training tasks. Theoretical analysis on the proposed ECNP establishes the relationship with CNP while offering deeper insights on the roles of the evidential parameters. Extensive experiments conducted on both synthetic and real-world data demonstrate the effectiveness of our proposed model in various few-shot settings.
PDF To appear in AAAI2023 Conference
点此查看论文截图
2022-12-02 更新
Data-Efficient Finetuning Using Cross-Task Nearest Neighbors
Authors:Hamish Ivison, Noah A. Smith, Hannaneh Hajishirzi, Pradeep Dasigi
Language models trained on massive prompted multitask datasets like T0 (Sanh et al., 2021) or FLAN (Wei et al., 2021a) can generalize to tasks unseen during training. We show that training on a carefully chosen subset of instances can outperform training on all available data on a variety of datasets. We assume access to a small number (250—1000) of unlabeled target task instances, select their nearest neighbors from a pool of multitask data, and use the retrieved data to train target task-specific models. Our method is more data-efficient than training a single multitask model, while still outperforming it by large margins. We evaluate across a diverse set of tasks not in the multitask pool we retrieve from, including those used to evaluate T0 and additional complex tasks including legal and scientific document QA. We retrieve small subsets of P3 (the collection of prompted datasets from which T0’s training data was sampled) and finetune T5 models that outperform the 3-billion parameter variant of T0 (T0-3B) by 3—30% on 12 out of 14 evaluation datasets while using at most 2% of the data used to train T0-3B. These models also provide a better initialization than T0-3B for few-shot finetuning on target-task data, as shown by a 2—23% relative improvement over few-shot finetuned T0-3B models on 8 datasets. Our code is available at https://github.com/allenai/data-efficient-finetuning.
PDF
点此查看论文截图
ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts
Authors:Akari Asai, Mohammadreza Salehi, Matthew E. Peters, Hannaneh Hajishirzi
This work introduces a new multi-task, parameter-efficient language model (LM) tuning method that learns to transfer knowledge across different tasks via a mixture of soft prompts-small prefix embedding vectors pre-trained for different tasks. Our method, called ATTEMPT (ATTEntional Mixtures of Prompt Tuning), obtains source prompts as encodings of large-scale source tasks into a small number of parameters and trains an attention module to interpolate the source prompts and a newly initialized target prompt for every instance in the target task. During training, only the target task prompt and the attention weights, which are shared between tasks in multi-task training, are updated, while the original LM and source prompts are intact. ATTEMPT is highly parameter-efficient (e.g., updates 2,300 times fewer parameters than full fine-tuning) while achieving high task performance using knowledge from high-resource tasks. Moreover, it is modular using pre-trained soft prompts, and can flexibly add or remove source prompts for effective knowledge transfer. Our experimental results across 21 diverse NLP datasets show that ATTEMPT significantly outperforms prompt tuning and outperforms or matches fully fine-tuned or other parameter-efficient tuning approaches that use over ten times more parameters. Finally, ATTEMPT outperforms previous work in few-shot learning settings.
PDF Published as a conference paper at EMNLP 2022 (long). Code available at https://github.com/AkariAsai/ATTEMPT
点此查看论文截图
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Authors:Yulei Qin, Xingyu Chen, Chao Chen, Yunhang Shen, Bo Ren, Yun Gu, Jie Yang, Chunhua Shen
Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain. However, only by tackling the performance gap above can we fully exploit the practical value of web datasets. To this end, we propose a Few-shot guided Prototypical (FoPro) representation learning method, which only needs a few labeled examples from reality and can significantly improve the performance in the real-world domain. Specifically, we initialize each class center with few-shot real-world data as the realistic" prototype. Then, the intra-class distance between web instances andrealistic” prototypes is narrowed by contrastive learning. Finally, we measure image-prototype distance with a learnable metric. Prototypes are polished by adjacent high-quality web images and involved in removing distant out-of-distribution samples. In experiments, FoPro is trained on web datasets with a few real-world examples guided and evaluated on real-world datasets. Our method achieves the state-of-the-art performance on three fine-grained datasets and two large-scale datasets. Compared with existing WSL methods under the same few-shot settings, FoPro still excels in real-world generalization. Code is available at https://github.com/yuleiqin/fopro.
PDF 7 pages, 5 figures, 5 tables. Accepted in AAAI 2023
点此查看论文截图
Finetune like you pretrain: Improved finetuning of zero-shot vision models
Authors:Sachin Goyal, Ananya Kumar, Sankalp Garg, Zico Kolter, Aditi Raghunathan
Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in the finetuning process can lead to surprisingly large differences in the final performance, both for in-distribution (ID) and out-of-distribution (OOD) data. In this work, we show that a natural and simple approach of mimicking contrastive pretraining consistently outperforms alternative finetuning approaches. Specifically, we cast downstream class labels as text prompts and continue optimizing the contrastive loss between image embeddings and class-descriptive prompt embeddings (contrastive finetuning). Our method consistently outperforms baselines across 7 distribution shifts, 6 transfer learning, and 3 few-shot learning benchmarks. On WILDS-iWILDCam, our proposed approach FLYP outperforms the top of the leaderboard by $2.3\%$ ID and $2.7\%$ OOD, giving the highest reported accuracy. Averaged across 7 OOD datasets (2 WILDS and 5 ImageNet associated shifts), FLYP gives gains of $4.2\%$ OOD over standard finetuning and outperforms the current state of the art (LP-FT) by more than $1\%$ both ID and OOD. Similarly, on 3 few-shot learning benchmarks, our approach gives gains up to $4.6\%$ over standard finetuning and $4.4\%$ over the state of the art. In total, these benchmarks establish contrastive finetuning as a simple, intuitive, and state-of-the-art approach for supervised finetuning of image-text models like CLIP. Code is available at https://github.com/locuslab/FLYP.
PDF 20 Pages, 7 Tables, 5 Figures
点此查看论文截图
On Utilizing Relationships for Transferable Few-Shot Fine-Grained Object Detection
Authors:Ambar Pal, Arnau Ramisa, Amit Kumar K C, René Vidal
State-of-the-art object detectors are fast and accurate, but they require a large amount of well annotated training data to obtain good performance. However, obtaining a large amount of training annotations specific to a particular task, i.e., fine-grained annotations, is costly in practice. In contrast, obtaining common-sense relationships from text, e.g., “a table-lamp is a lamp that sits on top of a table”, is much easier. Additionally, common-sense relationships like “on-top-of” are easy to annotate in a task-agnostic fashion. In this paper, we propose a probabilistic model that uses such relational knowledge to transform an off-the-shelf detector of coarse object categories (e.g., “table”, “lamp”) into a detector of fine-grained categories (e.g., “table-lamp”). We demonstrate that our method, RelDetect, achieves performance competitive to finetuning based state-of-the-art object detector baselines when an extremely low amount of fine-grained annotations is available ($0.2\%$ of entire dataset). We also demonstrate that RelDetect is able to utilize the inherent transferability of relationship information to obtain a better performance ($+5$ mAP points) than the above baselines on an unseen dataset (zero-shot transfer). In summary, we demonstrate the power of using relationships for object detection on datasets where fine-grained object categories can be linked to coarse-grained categories via suitable relationships.
PDF 8 pages, 3 figures
点此查看论文截图
One-shot recognition of any material anywhere using contrastive learning with physics-based rendering
Authors:Manuel S. Drehwald, Sagi Eppel, Jolina Li, Han Hao, Alan Aspuru-Guzik
We present MatSim: a synthetic dataset, a benchmark, and a method for computer vision based recognition of similarities and transitions between materials and textures, focusing on identifying any material under any conditions using one or a few examples (one-shot learning). The visual recognition of materials is essential to everything from examining food while cooking to inspecting agriculture, chemistry, and industrial products. In this work, we utilize giant repositories used by computer graphics artists to generate a new CGI dataset for material similarity. We use physics-based rendering (PBR) repositories for visual material simulation, assign these materials random 3D objects, and render images with a vast range of backgrounds and illumination conditions (HDRI). We add a gradual transition between materials to support applications with a smooth transition between states (like gradually cooked food). We also render materials inside transparent containers to support beverage and chemistry lab use cases. We then train a contrastive learning network to generate a descriptor that identifies unfamiliar materials using a single image. We also present a new benchmark for a few-shot material recognition that contains a wide range of real-world examples, including the state of a chemical reaction, rotten/fresh fruits, states of food, different types of construction materials, types of ground, and many other use cases involving material states, transitions and subclasses. We show that a network trained on the MatSim synthetic dataset outperforms state-of-the-art models like Clip on the benchmark, despite being tested on material classes that were not seen during training. The dataset, benchmark, code and trained models are available online.
PDF 11 pages, 8 figures, 1 table. for associated code, see https://e1.pcloud.link/publink/show?code=kZIiSQZCYU5M4HOvnQykql9jxF4h0KiC5MX and https://icedrive.net/s/A13FWzZ8V2aP9T4ufGQ1N3fBZxDF
点此查看论文截图