Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPosterior Differential Regularization with f-divergence for Improving Model Robustness
التنظيم التفاضلي الخلفي مع اختلاف F لتحسين النموذج
353
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نحن نبذة عن مشكلة تعزيز متانة النموذج من خلال التنظيم. على وجه التحديد، نركز على الأساليب التي تنظم الفرق الخلفي النموذجي بين المدخلات النظيفة والصاخبة. من الناحية النظرية، نحن نقدم اتصالا بطريقتين حديثين، وانتظام جاكوبي والتدريب الخصم الافتراضي، في إطار هذا الإطار. بالإضافة إلى ذلك، نعيد بتعميم التنظيم التفاضلي الخلفي لعائلة الاختلافات F وتوصيف الإطار العام من حيث مصفوفة الجاكوبيان. تجريبيا، قارنا هذه التحسينات وتدريب بيرت القياسي على مجموعة متنوعة من المهام لتوفير ملف شامل لتأثيرها على تعميم النموذج. لكلا الإعدادات ذات الإشراف بالكامل وشبه الإشراف، نوضح أن تنظيم الفرق الخلفي الذي يمكن أن يؤدي إلى اختلاف F إلى متانة نموذج جيد. على وجه الخصوص، مع اختلاف F-Supplgence مناسب، يمكن أن يحقق نموذج BERT-BASE تعميما قابلا للمقارنة كظرفي كبير لسيناريوهات التحول في المجال والمواد والمناطق، مما يشير إلى إمكانات كبيرة للإطار المقترح لتعزيز متانة نموذج NLP.
We address the problem of enhancing model robustness through regularization. Specifically, we focus on methods that regularize the model posterior difference between clean and noisy inputs. Theoretically, we provide a connection of two recent methods, Jacobian Regularization and Virtual Adversarial Training, under this framework. Additionally, we generalize the posterior differential regularization to the family of f-divergences and characterize the overall framework in terms of the Jacobian matrix. Empirically, we compare those regularizations and standard BERT training on a diverse set of tasks to provide a comprehensive profile of their effect on model generalization. For both fully supervised and semi-supervised settings, we show that regularizing the posterior difference with f-divergence can result in well-improved model robustness. In particular, with a proper f-divergence, a BERT-base model can achieve comparable generalization as its BERT-large counterpart for in-domain, adversarial and domain shift scenarios, indicating the great potential of the proposed framework for enhancing NLP model robustness.
References used
https://aclanthology.org/
rate research
Read More
While aggregate performance metrics can generate valuable insights at a large scale, their dominance means more complex and nuanced language phenomena, such as vagueness, may be overlooked. Focusing on vague terms (e.g. sunny, cloudy, young, etc.) we
inspect the behavior of visually grounded and text-only models, finding systematic divergences from human judgments even when a model's overall performance is high. To help explain this disparity, we identify two assumptions made by the datasets and models examined and, guided by the philosophy of vagueness, isolate cases where they do not hold.
Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much emphasis o
n how to well generalize models to new tasks. In this work, we propose an information disentanglement based regularization method for continual learning on text classification. Our proposed method first disentangles text hidden spaces into representations that are generic to all tasks and representations specific to each individual task, and further regularizes these representations differently to better constrain the knowledge required to generalize. We also introduce two simple auxiliary tasks: next sentence prediction and task-id prediction, for learning better generic and specific representation spaces. Experiments conducted on large-scale benchmarks demonstrate the effectiveness of our method in continual text classification tasks with various sequences and lengths over state-of-the-art baselines. We have publicly released our code at https://github.com/GT-SALT/IDBR.
Fine-tuning pre-trained language models suchas BERT has become a common practice dom-inating leaderboards across various NLP tasks.Despite its recent success and wide adoption,this process is unstable when there are onlya small number of training sam
ples available.The brittleness of this process is often reflectedby the sensitivity to random seeds. In this pa-per, we propose to tackle this problem basedon the noise stability property of deep nets,which is investigated in recent literature (Aroraet al., 2018; Sanyal et al., 2020). Specifically,we introduce a novel and effective regulariza-tion method to improve fine-tuning on NLPtasks, referred to asLayer-wiseNoiseStabilityRegularization (LNSR). We extend the theo-ries about adding noise to the input and provethat our method gives a stabler regularizationeffect. We provide supportive evidence by ex-perimentally confirming that well-performingmodels show a low sensitivity to noise andfine-tuning with LNSR exhibits clearly bet-ter generalizability and stability. Furthermore,our method also demonstrates advantages overother state-of-the-art algorithms including L2-SP (Li et al., 2018), Mixout (Lee et al., 2020)and SMART (Jiang et al., 20)
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often produce low
quality translations -- commonly failing to even produce outputs in the right target language. In this work, we observe that off-target translation is dominant even in strong multilingual systems, trained on massive multilingual corpora. To address this issue, we propose a joint approach to regularize NMT models at both representation-level and gradient-level. At the representation level, we leverage an auxiliary target language prediction task to regularize decoder outputs to retain information about the target language. At the gradient level, we leverage a small amount of direct data (in thousands of sentence pairs) to regularize model gradients. Our results demonstrate that our approach is highly effective in both reducing off-target translation occurrences and improving zero-shot translation performance by +5.59 and +10.38 BLEU on WMT and OPUS datasets respectively. Moreover, experiments show that our method also works well when the small amount of direct data is not available.
The robustness and security of natural language processing (NLP) models are significantly important in real-world applications. In the context of text classification tasks, adversarial examples can be designed by substituting words with synonyms unde
r certain semantic and syntactic constraints, such that a well-trained model will give a wrong prediction. Therefore, it is crucial to develop techniques to provide a rigorous and provable robustness guarantee against such attacks. In this paper, we propose WordDP to achieve certified robustness against word substitution at- tacks in text classification via differential privacy (DP). We establish the connection between DP and adversarial robustness for the first time in the text domain and propose a conceptual exponential mechanism-based algorithm to formally achieve the robustness. We further present a practical simulated exponential mechanism that has efficient inference with certified robustness. We not only provide a rigorous analytic derivation of the certified condition but also experimentally compare the utility of WordDP with existing defense algorithms. The results show that WordDP achieves higher accuracy and more than 30X efficiency improvement over the state-of-the-art certified robustness mechanism in typical text classification tasks.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
