Minwoo Lee

Archit Parnami, Minwoo Lee

Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples. Requiring a large number of data samples, many deep learning solutions suffer from data hunger and extensively high computation time and resources. Furthermore, data is often not available due to not only the nature of the problem or privacy concerns but also the cost of data preparation. Data collection, preprocessing, and labeling are strenuous human tasks. Therefore, few-shot learning that could drastically reduce the turnaround time of building machine learning applications emerges as a low-cost solution. This survey paper comprises a representative list of recently proposed few-shot learning algorithms. Given the learning dynamics and characteristics, the approaches to few-shot learning problems are discussed in the perspectives of meta-learning, transfer learning, and hybrid approaches (i.e., different variations of the few-shot learning problem).

Archit Parnami, Muhammad Usama, Liyue Fan et al.

Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains. However, deploying few-shot models in untrusted environments may inflict privacy concerns, e.g., attacks or adversaries that may breach the privacy of user-supplied data. This paper studies the privacy enhancement for the few-shot learning in an untrusted environment, e.g., the cloud, by establishing a novel privacy-preserved embedding space that preserves the privacy of data and maintains the accuracy of the model. We examine the impact of various image privacy methods such as blurring, pixelization, Gaussian noise, and differentially private pixelization (DP-Pix) on few-shot image classification and propose a method that learns privacy-preserved representation through the joint loss. The empirical results show how privacy-performance trade-off can be negotiated for privacy-enhanced few-shot learning.

Ziyan Wang, Enmao Diao, Qi Le et al.

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable for resource-constrained settings. To reduce computing and memory cost, pruning offers a promising solution by removing unimportant parameters. However, despite their success on standard LLMs, existing pruning methods severely damage RLMs, as even moderate sparsity (e.g., 20%) can collapse accuracy and completely disrupt the model's reasoning coherence. We begin by analyzing why existing pruning pipelines fail on reasoning LLMs and find that their brittleness largely stems from a mismatch between the calibration data, the pruning objective, and the model's decode-time reasoning behavior. Our study further shows that the most reliable calibration signal comes not from human-written labels but from the model's own self-generated reasoning traces, which more accurately reflect its inference distribution. Guided by these insights, we introduce RESP, a self-reflective structured pruning framework that aligns pruning decisions with the model's reasoning dynamics through self-generated calibration, decode-only gradient-based importance estimation, and progressive regeneration that maintains calibration fidelity as sparsity increases. Experiments on Qwen3-8B demonstrate that RESP markedly outperforms existing structured pruning methods on both GSM8K and MathQA, preserving near-dense accuracy at 20-30% sparsity and substantially mitigating performance collapse at higher sparsity levels. At 40% sparsity, RESP attains 81.3% accuracy on GSM8K and 59.6% on MathQA, surpassing the strongest baselines by 66.87% and 47%, respectively.

Matias Mendieta, Taojiannan Yang, Pu Wang et al.

Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nature, making efficient optimization difficult. To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model. Instead, we consider rethinking solutions to data heterogeneity in FL with a focus on local learning generality rather than proximal restriction. To this end, we first present a systematic study informed by second-order indicators to better understand algorithm effectiveness in FL. Interestingly, we find that standard regularization methods are surprisingly strong performers in mitigating data heterogeneity effects. Based on our findings, we further propose a simple and effective method, FedAlign, to overcome data heterogeneity and the pitfalls of previous methods. FedAlign achieves competitive accuracy with state-of-the-art FL methods across a variety of settings while minimizing computation and memory overhead. Code is available at https://github.com/mmendiet/FedAlign

Taojiannan Yang, Sijie Zhu, Matias Mendieta et al.

Most existing deep neural networks are static, which means they can only do inference at a fixed complexity. But the resource budget can vary substantially across different devices. Even on a single device, the affordable budget can change with different scenarios, and repeatedly training networks for each required budget would be incredibly expensive. Therefore, in this work, we propose a general method called MutualNet to train a single network that can run at a diverse set of resource constraints. Our method trains a cohort of model configurations with various network widths and input resolutions. This mutual learning scheme not only allows the model to run at different width-resolution configurations but also transfers the unique knowledge among these configurations, helping the model to learn stronger representations overall. MutualNet is a general training methodology that can be applied to various network structures (e.g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e.g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets. Since we only train the model once, it also greatly reduces the training cost compared to independently training several models. Surprisingly, MutualNet can also be used to significantly boost the performance of a single network, if dynamic resource constraint is not a concern. In summary, MutualNet is a unified method for both static and adaptive, 2D and 3D networks. Codes and pre-trained models are available at \url{https://github.com/taoyang1122/MutualNet}.

Dongryeol Lee, Minwoo Lee, Kyungmin Min et al.

Recently, directly using large language models (LLMs) has been shown to be the most reliable method to evaluate QA models. However, it suffers from limited interpretability, high cost, and environmental harm. To address these, we propose to use soft EM with entity-driven answer set expansion. Our approach expands the gold answer set to include diverse surface forms, based on the observation that the surface forms often follow particular patterns depending on the entity type. The experimental results show that our method outperforms traditional evaluation methods by a large margin. Moreover, the reliability of our evaluation method is comparable to that of LLM-based ones, while offering the benefits of high interpretability and reduced environmental harm.

Ziyan Wang, Enmao Diao, Qi Le et al.

Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local paradigm is task-agnostic: by optimizing layer-wise reconstruction rather than task objectives, it tends to preserve perplexity or generic zero-shot behavior but fails to capitalize on modest task-specific calibration signals, often yielding limited downstream gains. We revisit global structured pruning and present GISP-Global Iterative Structured Pruning-a post-training method that removes attention heads and MLP channels using first-order, loss-based important weights aggregated at the structure level with block-wise normalization. An iterative schedule, rather than one-shot pruning, stabilizes accuracy at higher sparsity and mitigates perplexity collapse without requiring intermediate fine-tuning; the pruning trajectory also forms nested subnetworks that support a "prune-once, deploy-many" workflow. Furthermore, because importance is defined by a model-level loss, GISP naturally supports task-specific objectives; we instantiate perplexity for language modeling and a margin-based objective for decision-style tasks. Extensive experiments show that across Llama2-7B/13B, Llama3-8B, and Mistral-0.3-7B, GISP consistently lowers WikiText-2 perplexity and improves downstream accuracy, with especially strong gains at 40-50% sparsity; on DeepSeek-R1-Distill-Llama-3-8B with GSM8K, task-aligned calibration substantially boosts exact-match accuracy.

Minwoo Lee, Hyukhun Koh, Kang-il Lee et al.

Gender bias is a significant issue in machine translation, leading to ongoing research efforts in developing bias mitigation techniques. However, most works focus on debiasing bilingual models without much consideration for multilingual systems. In this paper, we specifically target the gender bias issue of multilingual machine translation models for unambiguous cases where there is a single correct translation, and propose a bias mitigation method based on a novel approach. Specifically, we propose Gender-Aware Contrastive Learning, GACL, which encodes contextual gender information into the representations of non-explicit gender words. Our method is target language-agnostic and is applicable to pre-trained multilingual machine translation models via fine-tuning. Through multilingual evaluation, we show that our approach improves gender accuracy by a wide margin without hampering translation performance. We also observe that incorporated gender information transfers and benefits other target languages regarding gender accuracy. Finally, we demonstrate that our method is applicable and beneficial to models of various sizes.

Dongryeol Lee, Segwang Kim, Minwoo Lee et al.

Ambiguous questions persist in open-domain question answering, because formulating a precise question with a unique answer is often challenging. Previously, Min et al. (2020) have tackled this issue by generating disambiguated questions for all possible interpretations of the ambiguous question. This can be effective, but not ideal for providing an answer to the user. Instead, we propose to ask a clarification question, where the user's response will help identify the interpretation that best aligns with the user's intention. We first present CAMBIGNQ, a dataset consisting of 5,654 ambiguous questions, each with relevant passages, possible answers, and a clarification question. The clarification questions were efficiently created by generating them using InstructGPT and manually revising them as necessary. We then define a pipeline of tasks and design appropriate evaluation metrics. Lastly, we achieve 61.3 F1 on ambiguity detection and 40.5 F1 on clarification-based QA, providing strong baselines for future work.

Archit Parnami, Mayuri Deshpande, Anant Kumar Mishra et al.

Recent advances in neural networks have solved common graph problems such as link prediction, node classification, node clustering, node recommendation by developing embeddings of entities and relations into vector spaces. Graph embeddings encode the structural information present in a graph. The encoded embeddings then can be used to predict the missing links in a graph. However, obtaining the optimal embeddings for a graph can be a computationally challenging task specially in an embedded system. Two techniques which we focus on in this work are 1) node embeddings from random walk based methods and 2) knowledge graph embeddings. Random walk based embeddings are computationally inexpensive to obtain but are sub-optimal whereas knowledge graph embeddings perform better but are computationally expensive. In this work, we investigate a transformation model which converts node embeddings obtained from random walk based methods to embeddings obtained from knowledge graph methods directly without an increase in the computational cost. Extensive experimentation shows that the proposed transformation model can be used for solving link prediction in real-time.

Giang Dao, Minwoo Lee

Modern deep learning algorithms tend to optimize an objective metric, such as minimize a cross entropy loss on a training dataset, to be able to learn. The problem is that the single metric is an incomplete description of the real world tasks. The single metric cannot explain why the algorithm learn. When an erroneous happens, the lack of interpretability causes a hardness of understanding and fixing the error. Recently, there are works done to tackle the problem of interpretability to provide insights into neural networks behavior and thought process. The works are important to identify potential bias and to ensure algorithm fairness as well as expected performance.

Archit Parnami, Minwoo Lee

Recognizing a particular command or a keyword, keyword spotting has been widely used in many voice interfaces such as Amazon's Alexa and Google Home. In order to recognize a set of keywords, most of the recent deep learning based approaches use a neural network trained with a large number of samples to identify certain pre-defined keywords. This restricts the system from recognizing new, user-defined keywords. Therefore, we first formulate this problem as a few-shot keyword spotting and approach it using metric learning. To enable this research, we also synthesize and publish a Few-shot Google Speech Commands dataset. We then propose a solution to the few-shot keyword spotting problem using temporal and dilated convolutions on prototypical networks. Our comparative experimental results demonstrate keyword spotting of new keywords using just a small number of samples.

Nancy Amato, Charles Anderson, Gregory Chirikjian et al.

Proceedings of the 1st International Workshop on Robot Learning and Planning (RLP 2016)