More Like this

1. Embarrassingly Simple Dataset Distillation

   Feng, Yunzhen; Vedantam, Shanmukha; Kempe, Julia (May 2024, International Conference on Learning Representations)

   Dataset distillation extracts a small set of synthetic training samples from a large dataset with the goal of achieving competitive performance on test data when trained on this sample. In this work, we tackle dataset distillation at its core by treating it directly as a bilevel optimization problem. Re-examining the foundational back-propagation through time method, we study the pronounced variance in the gradients, computational burden, and long-term dependencies. We introduce an improved method: Random Truncated Backpropagation Through Time (RaT-BPTT) to address them. RaT-BPTT incorporates a truncation coupled with a random window, effectively stabilizing the gradients and speeding up the optimization while covering long dependencies. This allows us to establish new state-of-the-art for a variety of standard dataset benchmarks. A deeper dive into the nature of distilled data unveils pronounced intercorrelation. In particular, subsets of distilled datasets tend to exhibit much worse performance than directly distilled smaller datasets of the same size. Leveraging RaT-BPTT, we devise a boosting mechanism that generates distilled datasets that contain subsets with near optimal performance across different data budgets. 

   more » « less
2. Specialized Embedding Approximation for Edge Intelligence: A Case Study in Urban Sound Classification

   https://doi.org/10.1109/ICASSP39728.2021.9414287  

   Srivastava, Sangeeta; Roy, Dhrubojyoti; Cartwright, Mark; Bello, Juan P.; Arora, Anish (June 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP))

   null (Ed.)

   Embedding models that encode semantic information into low-dimensional vector representations are useful in various machine learning tasks with limited training data. However, these models are typically too large to support inference in small edge devices, which motivates training of smaller yet comparably predictive student embedding models through knowledge distillation (KD). While knowledge distillation traditionally uses the teacher’s original training dataset to train the student, we hypothesize that using a dataset similar to the student’s target domain allows for better compression and training efficiency for the said domain, at the cost of reduced generality across other (non-pertinent) domains. Hence, we introduce Specialized Embedding Approximation (SEA) to train a student featurizer to approximate the teacher’s embedding manifold for a given target domain. We demonstrate the feasibility of SEA in the context of acoustic event classification for urban noise monitoring and show that leveraging a dataset related to this target domain not only improves the baseline performance of the original embedding model but also yields competitive students with >1 order of magnitude lesser storage and activation memory. We further investigate the impact of using random and informed sampling techniques for dimensionality reduction in SEA. 

   more » « less
3. Self-trainable and adaptive sensor intelligence for selective data generation

   https://doi.org/10.3389/frai.2024.1403187  

   Rezvani, Arghavan; Huang, Wenjun; Chen, Hanning; Ni, Yang; Imani, Mohsen (January 2025, Frontiers in Artificial Intelligence)

   With the increasing integration of machine learning into IoT devices, managing energy consumption and data transmission has become a critical challenge. Many IoT applications depend on complex computations performed on server-side infrastructure, necessitating efficient methods to reduce unnecessary data transmission. One promising solution involves deploying compact machine learning models near sensors, enabling intelligent identification and transmission of only relevant data frames. However, existing near-sensor models lack adaptability, as they require extensive pre-training and are often rigidly configured prior to deployment. This paper proposes a novel framework that fuses online learning, active learning, and knowledge distillation to enable adaptive, resource-efficient near-sensor intelligence. Our approach allows near-sensor models to dynamically fine-tune their parameters post-deployment using online learning, eliminating the need for extensive pre-labeling and training. Through a sequential training and execution process, the framework achieves continuous adaptability without prior knowledge of the deployment environment. To enhance performance while preserving model efficiency, we integrate knowledge distillation, enabling the transfer of critical insights from a larger teacher model to a compact student model. Additionally, active learning reduces the required training data while maintaining competitive performance. We validated our framework on both benchmark data from the MS COCO dataset and in a simulated IoT environment. The results demonstrate significant improvements in energy efficiency and data transmission optimization, highlighting the practical applicability of our method in real-world IoT scenarios. 

   more » « less
4. Does Knowledge Distillation Really Work?

   Stanton, Samuel; Izmailov, Pavel; Kirichenko, Polina; Alemi, Alexander A.; Wilson, Andrew G. (January 2021, Advances in neural information processing systems)

   Knowledge distillation is a popular technique for training a small student network to emulate a larger teacher model, such as an ensemble of networks. We show that while knowledge distillation can improve student generalization, it does not typically work as it is commonly understood: there often remains a surprisingly large discrepancy between the predictive distributions of the teacher and the student, even in cases when the student has the capacity to perfectly match the teacher. We identify difficulties in optimization as a key reason for why the student is unable to match the teacher. We also show how the details of the dataset used for distillation play a role in how closely the student matches the teacher --- and that more closely matching the teacher paradoxically does not always lead to better student generalization. 

   more » « less
5. Improving RNA secondary structure prediction via state inference with deep recurrent neural networks

   https://doi.org/10.1515/cmb-2020-0002  

   Willmott, Devin; Murrugarra, David; Ye, Qiang (March 2020, Computational and Mathematical Biophysics)

   Abstract The problem of determining which nucleotides of an RNA sequence are paired or unpaired in the secondary structure of an RNA, which we call RNA state inference, can be studied by different machine learning techniques. Successful state inference of RNA sequences can be used to generate auxiliary information for data-directed RNA secondary structure prediction. Typical tools for state inference, such as hidden Markov models, exhibit poor performance in RNA state inference, owing in part to their inability to recognize nonlocal dependencies. Bidirectional long short-term memory (LSTM) neural networks have emerged as a powerful tool that can model global nonlinear sequence dependencies and have achieved state-of-the-art performances on many different classification problems. This paper presents a practical approach to RNA secondary structure inference centered around a deep learning method for state inference. State predictions from a deep bidirectional LSTM are used to generate synthetic SHAPE data that can be incorporated into RNA secondary structure prediction via the Nearest Neighbor Thermodynamic Model (NNTM). This method produces predicted secondary structures for a diverse test set of 16S ribosomal RNA that are, on average, 25 percentage points more accurate than undirected MFE structures. Accuracy is highly dependent on the success of our state inference method, and investigating the global features of our state predictions reveals that accuracy of both our state inference and structure inference methods are highly dependent on the similarity of pairing patterns of the sequence to the training dataset. Availability of a large training dataset is critical to the success of this approach. Code available at https://github.com/dwillmott/rna-state-inf . 

   more » « less