2023-01-26 更新
Adapting a Language Model While Preserving its General Knowledge
Authors:Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu
Domain-adaptive pre-training (or DA-training for short), also known as post-training, aims to train a pre-trained general-purpose language model (LM) using an unlabeled corpus of a particular domain to adapt the LM so that end-tasks in the domain can give improved performances. However, existing DA-training methods are in some sense blind as they do not explicitly identify what knowledge in the LM should be preserved and what should be changed by the domain corpus. This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge. Experimental results will demonstrate the effectiveness of the proposed approach.
PDF EMNLP 2022
点此查看论文截图
One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER
Authors:Xiang Chen, Lei Li, Qiaoshuo Fei, Ningyu Zhang, Chuanqi Tan, Yong Jiang, Fei Huang, Huajun Chen
Cross-domain NER is a challenging task to address the low-resource problem in practical scenarios. Previous typical solutions mainly obtain a NER model by pre-trained language models (PLMs) with data from a rich-resource domain and adapt it to the target domain. Owing to the mismatch issue among entity types in different domains, previous approaches normally tune all parameters of PLMs, ending up with an entirely new NER model for each domain. Moreover, current models only focus on leveraging knowledge in one general source domain while failing to successfully transfer knowledge from multiple sources to the target. To address these issues, we introduce Collaborative Domain-Prefix Tuning for cross-domain NER (CP-NER) based on text-to-text generative PLMs. Specifically, we present text-to-text generation grounding domain-related instructors to transfer knowledge to new domain NER tasks without structural modifications. We utilize frozen PLMs and conduct collaborative domain-prefix tuning to stimulate the potential of PLMs to handle NER tasks across various domains. Experimental results on the Cross-NER benchmark show that the proposed approach has flexible transfer ability and performs better on both one-source and multiple-source cross-domain NER tasks. Codes will be available in https://github.com/zjunlp/DeepKE/tree/main/example/ner/cross.
PDF Work in progress
点此查看论文截图
When does the student surpass the teacher? Federated Semi-supervised Learning with Teacher-Student EMA
Authors:Jessica Zhao, Sayan Ghosh, Akash Bharadwaj, Chih-Yao Ma
Semi-Supervised Learning (SSL) has received extensive attention in the domain of computer vision, leading to development of promising approaches such as FixMatch. In scenarios where training data is decentralized and resides on client devices, SSL must be integrated with privacy-aware training techniques such as Federated Learning. We consider the problem of federated image classification and study the performance and privacy challenges with existing federated SSL (FSSL) approaches. Firstly, we note that even state-of-the-art FSSL algorithms can trivially compromise client privacy and other real-world constraints such as client statelessness and communication cost. Secondly, we observe that it is challenging to integrate EMA (Exponential Moving Average) updates into the federated setting, which comes at a trade-off between performance and communication cost. We propose a novel approach FedSwitch, that improves privacy as well as generalization performance through Exponential Moving Average (EMA) updates. FedSwitch utilizes a federated semi-supervised teacher-student EMA framework with two features - local teacher adaptation and adaptive switching between teacher and student for pseudo-label generation. Our proposed approach outperforms the state-of-the-art on federated image classification, can be adapted to real-world constraints, and achieves good generalization performance with minimal communication cost overhead.
PDF
点此查看论文截图
Low-Resource Compositional Semantic Parsing with Concept Pretraining
Authors:Subendhu Rongali, Mukund Sridhar Harakere, Haidar Khan, Konstantine Arkoudas, Wael Hamza, Andrew McCallum
Semantic parsing plays a key role in digital voice assistants such as Alexa, Siri, and Google Assistant by mapping natural language to structured meaning representations. When we want to improve the capabilities of a voice assistant by adding a new domain, the underlying semantic parsing model needs to be retrained using thousands of annotated examples from the new domain, which is time-consuming and expensive. In this work, we present an architecture to perform such domain adaptation automatically, with only a small amount of metadata about the new domain and without any new training data (zero-shot) or with very few examples (few-shot). We use a base seq2seq (sequence-to-sequence) architecture and augment it with a concept encoder that encodes intent and slot tags from the new domain. We also introduce a novel decoder-focused approach to pretrain seq2seq models to be concept aware using Wikidata and use it to help our model learn important concepts and perform well in low-resource settings. We report few-shot and zero-shot results for compositional semantic parsing on the TOPv2 dataset and show that our model outperforms prior approaches in few-shot settings for the TOPv2 and SNIPS datasets.
PDF EACL 2023
点此查看论文截图
Discriminator-free Unsupervised Domain Adaptation for Multi-label Image Classification
Authors:Indel Pal Singh, Enjie Ghorbel, Anis Kacem, Arunkumar Rathinam, Djamila Aouada
In this paper, a discriminator-free adversarial-based Unsupervised Domain Adaptation (UDA) for Multi-Label Image Classification (MLIC) referred to as DDA-MLIC is proposed. Over the last two years, some attempts have been made for introducing adversarial-based UDA methods in the context of MLIC. However, these methods which rely on an additional discriminator subnet present two shortcomings. First, the learning of domain-invariant features may harm their task-specific discriminative power, since the classification and discrimination tasks are decoupled. Moreover, the use of an additional discriminator usually induces an increase of the network size. Herein, we propose to overcome these issues by introducing a novel adversarial critic that is directly deduced from the task-specific classifier. Specifically, a two-component Gaussian Mixture Model (GMM) is fitted on the source and target predictions, allowing the distinction of two clusters. This allows extracting a Gaussian distribution for each component. The resulting Gaussian distributions are then used for formulating an adversarial loss based on a Frechet distance. The proposed method is evaluated on three multi-label image datasets. The obtained results demonstrate that DDA-MLIC outperforms existing state-of-the-art methods while requiring a lower number of parameters.
PDF
点此查看论文截图
Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding
Authors:Juncheng Li, Siliang Tang, Linchao Zhu, Wenqiao Zhang, Yi Yang, Tat-Seng Chua, Fei Wu, Yueting Zhuang
Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. This task has achieved significant momentum in the computer vision community as it enables activity grounding beyond pre-defined activity classes by utilizing the semantic diversity of natural language descriptions. The semantic diversity is rooted in the principle of compositionality in linguistics, where novel semantics can be systematically described by combining known words in novel ways (compositional generalization). However, existing temporal grounding datasets are not carefully designed to evaluate the compositional generalizability. To systematically benchmark the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i.e., Charades-CG and ActivityNet-CG. When evaluating the state-of-the-art methods on our new dataset splits, we empirically find that they fail to generalize to queries with novel combinations of seen words. We argue that the inherent structured semantics inside the videos and language is the crucial factor to achieve compositional generalization. Based on this insight, we propose a variational cross-graph reasoning framework that explicitly decomposes video and language into hierarchical semantic graphs, respectively, and learns fine-grained semantic correspondence between the two graphs. Furthermore, we introduce a novel adaptive structured semantics learning approach to derive the structure-informed and domain-generalizable graph representations, which facilitate the fine-grained semantic correspondence reasoning between the two graphs. Extensive experiments validate the superior compositional generalizability of our approach.
PDF arXiv admin note: substantial text overlap with arXiv:2203.13049
点此查看论文截图
Spectral Cross-Domain Neural Network with Soft-adaptive Threshold Spectral Enhancement
Authors:Che Liu, Sibo Cheng, Weiping Ding, Rossella Arcucci
Electrocardiography (ECG) signals can be considered as multi-variable time-series. The state-of-the-art ECG data classification approaches, based on either feature engineering or deep learning techniques, treat separately spectral and time domains in machine learning systems. No spectral-time domain communication mechanism inside the classifier model can be found in current approaches, leading to difficulties in identifying complex ECG forms. In this paper, we proposed a novel deep learning model named Spectral Cross-domain neural network (SCDNN) with a new block called Soft-adaptive threshold spectral enhancement (SATSE), to simultaneously reveal the key information embedded in spectral and time domains inside the neural network. More precisely, the domain-cross information is captured by a general Convolutional neural network (CNN) backbone, and different information sources are merged by a self-adaptive mechanism to mine the connection between time and spectral domains. In SATSE, the knowledge from time and spectral domains is extracted via the Fast Fourier Transformation (FFT) with soft trainable thresholds in modified Sigmoid functions. The proposed SCDNN is tested with several classification tasks implemented on the public ECG databases \textit{PTB-XL} and \textit{MIT-BIH}. SCDNN outperforms the state-of-the-art approaches with a low computational cost regarding a variety of metrics in all classification tasks on both databases, by finding appropriate domains from the infinite spectral mapping. The convergence of the trainable thresholds in the spectral domain is also numerically investigated in this paper. The robust performance of SCDNN provides a new perspective to exploit knowledge across deep learning models from time and spectral domains. The repository can be found: https://github.com/DL-WG/SCDNN-TS
PDF
点此查看论文截图
When Source-Free Domain Adaptation Meets Label Propagation
Authors:Chunwei Wu, Guitao Cao, Yan Li, Xidong Xi, Wenming Cao, Hong Wang
Source-free domain adaptation, where only a pre-trained source model is used to adapt to the target distribution, is a more general approach to achieving domain adaptation. However, it can be challenging to capture the inherent structure of the target features accurately due to the lack of supervised information on the target domain. To tackle this problem, we propose a novel approach called Adaptive Local Transfer (ALT) that tries to achieve efficient feature clustering from the perspective of label propagation. ALT divides the target data into inner and outlier samples based on the adaptive threshold of the learning state, and applies a customized learning strategy to best fits the data property. Specifically, inner samples are utilized for learning intra-class structure thanks to their relatively well-clustered properties. The low-density outlier samples are regularized by input consistency to achieve high accuracy with respect to the ground truth labels. In this way, local clustering can be prevented from forming spurious clusters while effectively propagating label information among subpopulations. Empirical evidence demonstrates that ALT outperforms the state of the arts on three public benchmarks: Office-31, Office-Home, and VisDA.
PDF
点此查看论文截图
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Authors:Megan M. Baker, Alexander New, Mario Aguilar-Simon, Ziad Al-Halah, Sébastien M. R. Arnold, Ese Ben-Iwhiwhu, Andrew P. Brna, Ethan Brooks, Ryan C. Brown, Zachary Daniels, Anurag Daram, Fabien Delattre, Ryan Dellana, Eric Eaton, Haotian Fu, Kristen Grauman, Jesse Hostetler, Shariq Iqbal, Cassandra Kent, Nicholas Ketz, Soheil Kolouri, George Konidaris, Dhireesha Kudithipudi, Erik Learned-Miller, Seungwon Lee, Michael L. Littman, Sandeep Madireddy, Jorge A. Mendez, Eric Q. Nguyen, Christine D. Piatko, Praveen K. Pilly, Aswin Raghavan, Abrar Rahman, Santhosh Kumar Ramakrishnan, Neale Ratzlaff, Andrea Soltoggio, Peter Stone, Indranil Sur, Zhipeng Tang, Saket Tiwari, Kyle Vedder, Felix Wang, Zifan Xu, Angel Yanguas-Gil, Harel Yedidsion, Shangqun Yu, Gautam K. Vallabha
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to “real world” events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of “Lifelong Learning” systems that are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future.
PDF To appear in Neural Networks
点此查看论文截图
DEJA VU: Continual Model Generalization For Unseen Domains
Authors:Chenxi Liu, Lixu Wang, Lingjuan Lyu, Chen Sun, Xiao Wang, Qi Zhu
In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline modes to improve cross-domain adaptation ability. However, these DA methods typically only provide good performance after a long period of adaptation, and perform poorly on new domains before and during adaptation - in what we call the “Unfamiliar Period”, especially when domain shifts happen suddenly and significantly. On the other hand, domain generalization (DG) methods have been proposed to improve the model generalization ability on unadapted domains. However, existing DG works are ineffective for continually changing domains due to severe catastrophic forgetting of learned knowledge. To overcome these limitations of DA and DG in handling the Unfamiliar Period during continual domain shift, we propose RaTP, a framework that focuses on improving models’ target domain generalization (TDG) capability, while also achieving effective target domain adaptation (TDA) capability right after training on certain domains and forgetting alleviation (FA) capability on past domains. RaTP includes a training-free data augmentation module to prepare data for TDG, a novel pseudo-labeling mechanism to provide reliable supervision for TDA, and a prototype contrastive alignment algorithm to align different domains for achieving TDG, TDA and FA. Extensive experiments on Digits, PACS, and DomainNet demonstrate that RaTP significantly outperforms state-of-the-art works from Continual DA, Source-Free DA, Test-Time/Online DA, Single DG, Multiple DG and Unified DA&DG in TDG, and achieves comparable TDA and FA capabilities.
PDF Published as a conference paper at ICLR 2023
点此查看论文截图
Tracking Different Ant Species: An Unsupervised Domain Adaptation Framework and a Dataset for Multi-object Tracking
Authors:Chamath Abeysinghe, Chris Reid, Hamid Rezatofighi, Bernd Meyer
Tracking individuals is a vital part of many experiments conducted to understand collective behaviour. Ants are the paradigmatic model system for such experiments but their lack of individually distinguishing visual features and their high colony densities make it extremely difficult to perform reliable tracking automatically. Additionally, the wide diversity of their species’ appearances makes a generalized approach even harder. In this paper, we propose a data-driven multi-object tracker that, for the first time, employs domain adaptation to achieve the required generalisation. This approach is built upon a joint-detection-and-tracking framework that is extended by a set of domain discriminator modules integrating an adversarial training strategy in addition to the tracking loss. In addition to this novel domain-adaptive tracking framework, we present a new dataset and a benchmark for the ant tracking problem. The dataset contains 57 video sequences with full trajectory annotation, including 30k frames captured from two different ant species moving on different background patterns. It comprises 33 and 24 sequences for source and target domains, respectively. We compare our proposed framework against other domain-adaptive and non-domain-adaptive multi-object tracking baselines using this dataset and show that incorporating domain adaptation at multiple levels of the tracking pipeline yields significant improvements. The code and the dataset are available at https://github.com/chamathabeysinghe/da-tracker.
PDF
点此查看论文截图