Sahib Singh

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al. · allen-ai, amazon-science

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli et al. · mila

Africa has a very low doctor-to-patient ratio. At very busy clinics, doctors could see 30+ patients per day -- a heavy patient burden compared with developed countries -- but productivity tools such as clinical automatic speech recognition (ASR) are lacking for these overworked clinicians. However, clinical ASR is mature, even ubiquitous, in developed nations, and clinician-reported performance of commercial clinical ASR systems is generally satisfactory. Furthermore, the recent performance of general domain ASR is approaching human accuracy. However, several gaps exist. Several publications have highlighted racial bias with speech-to-text algorithms and performance on minority accents lags significantly. To our knowledge, there is no publicly available research or benchmark on accented African clinical ASR, and speech data is non-existent for the majority of African accents. We release AfriSpeech, 200hrs of Pan-African English speech, 67,577 clips from 2,463 unique speakers across 120 indigenous accents from 13 countries for clinical and general domain ASR, a benchmark test set, with publicly available pre-trained models with SOTA performance on the AfriSpeech benchmark.

Tobi Olatunji, Tejumade Afonja, Bonaventure F. P. Dossou et al. · mila

Useful conversational agents must accurately capture named entities to minimize error for downstream tasks, for example, asking a voice assistant to play a track from a certain artist, initiating navigation to a specific location, or documenting a laboratory result for a patient. However, where named entities such as ``Ukachukwu`` (Igbo), ``Lakicia`` (Swahili), or ``Ingabire`` (Rwandan) are spoken, automatic speech recognition (ASR) models' performance degrades significantly, propagating errors to downstream systems. We model this problem as a distribution shift and demonstrate that such model bias can be mitigated through multilingual pre-training, intelligent data augmentation strategies to increase the representation of African-named entities, and fine-tuning multilingual ASR models on multiple African accents. The resulting fine-tuned models show an 81.5\% relative WER improvement compared with the baseline on samples with African-named entities.

Idris Abdulmumin, Michael Beukman, Jesujoba O. Alabi et al.

We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the given noisy data using a sentence-pair classifier that was built by fine-tuning a pre-trained language model. To train the classifier, we obtain positive samples (i.e. high-quality parallel sentences) from a gold-standard curated dataset and extract negative samples (i.e. low-quality parallel sentences) from automatically aligned parallel data by choosing sentences with low alignment scores. Our final machine translation model was then trained on filtered data, instead of the entire noisy dataset. We empirically validate our approach by evaluating on two common datasets and show that data filtering generally improves overall translation quality, in some cases even significantly.

Priyam Basu, Tiasa Singha Roy, Rakshit Naidu et al.

Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depression is a serious medical illness that can have adverse effects on how one feels, thinks, and acts, which can lead to emotional and physical problems. Due to the sensitive nature of such data, privacy measures need to be taken for handling and training models with such data. In this work, we study the effects that the application of Differential Privacy (DP) has, in both a centralized and a Federated Learning (FL) setup, on training contextualized language models (BERT, ALBERT, RoBERTa and DistilBERT). We offer insights on how to privately train NLP models and what architectures and setups provide more desirable privacy utility trade-offs. We envisage this work to be used in future healthcare and mental health studies to keep medical history private. Therefore, we provide an open-source implementation of this work.

Ayush Manish Agrawal, Atharva Tendle, Harshvardhan Sikka et al.

Interpreting the learning dynamics of neural networks can provide useful insights into how networks learn and the development of better training and design approaches. We present an approach to interpret learning in neural networks by measuring relative weight change on a per layer basis and dynamically aggregating emerging trends through combination of dimensionality reduction and clustering which allows us to scale to very deep networks. We use this approach to investigate learning in the context of vision tasks across a variety of state-of-the-art networks and provide insights into the learning behavior of these networks, including how task complexity affects layer-wise learning in deeper layers of networks.

Sahib Singh, Rosanne Liu

Recent studies assessing the efficacy of pruning neural networks methods uncovered a surprising finding: when conducting ablation studies on existing pruning-at-initialization methods, namely SNIP, GraSP, SynFlow, and magnitude pruning, performances of these methods remain unchanged and sometimes even improve when randomly shuffling the mask positions within each layer (Layerwise Shuffling) or sampling new initial weight values (Reinit), while keeping pruning masks the same. We attempt to understand the reason behind such network immunity towards weight/mask modifications, by studying layer-wise statistics before and after randomization operations. We found that under each of the pruning-at-initialization methods, the distribution of unpruned weights changed minimally with randomization operations.

Nelson Manohar-Alers, Ryan Feng, Sahib Singh et al.

We present DeClaW, a system for detecting, classifying, and warning of adversarial inputs presented to a classification neural network. In contrast to current state-of-the-art methods that, given an input, detect whether an input is clean or adversarial, we aim to also identify the types of adversarial attack (e.g., PGD, Carlini-Wagner or clean). To achieve this, we extract statistical profiles, which we term as anomaly feature vectors, from a set of latent features. Preliminary findings suggest that AFVs can help distinguish among several types of adversarial attacks (e.g., PGD versus Carlini-Wagner) with close to 93% accuracy on the CIFAR-10 dataset. The results open the door to using AFV-based methods for exploring not only adversarial attack detection but also classification of the attack type and then design of attack-specific mitigation strategies.

Archit Uniyal, Rakshit Naidu, Sasikanth Kotti et al.

Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on different sub-groups in the population, which leads to a significantly high drop-in model utility for sub-populations that are under-represented (minorities), compared to well-represented ones. In this work, we aim to compare PATE, another mechanism for training deep learning models using differential privacy, with DP-SGD in terms of fairness. We show that PATE does have a disparate impact too, however, it is much less severe than DP-SGD. We draw insights from this observation on what might be promising directions in achieving better fairness-privacy trade-offs.

Ayush Manish Agrawal, Atharva Tendle, Harshvardhan Sikka et al.

Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. We investigate learning in Deep Convolutional Neural Networks (CNNs) by measuring the relative weight change of layers while training. Several interesting trends emerge in a variety of CNN architectures across various computer vision classification tasks, including the overall increase in relative weight change of later layers as compared to earlier ones.

Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh et al.

Deployment of deep learning in different fields and industries is growing day by day due to its performance, which relies on the availability of data and compute. Data is often crowd-sourced and contains sensitive information about its contributors, which leaks into models that are trained on it. To achieve rigorous privacy guarantees, differentially private training mechanisms are used. However, it has recently been shown that differential privacy can exacerbate existing biases in the data and have disparate impacts on the accuracy of different subgroups of data. In this paper, we aim to study these effects within differentially private deep learning. Specifically, we aim to study how different levels of imbalance in the data affect the accuracy and the fairness of the decisions made by the model, given different levels of privacy. We demonstrate that even small imbalances and loose privacy guarantees can cause disparate impacts.

Sahib Singh, Harshvardhan Sikka, Sasikanth Kotti et al.

In this paper we measure the effectiveness of $ε$-Differential Privacy (DP) when applied to medical imaging. We compare two robust differential privacy mechanisms: Local-DP and DP-SGD and benchmark their performance when analyzing medical imagery records. We analyze the trade-off between the model's accuracy and the level of privacy it guarantees, and also take a closer look to evaluate how useful these theoretical privacy guarantees actually prove to be in the real world medical setting.