Yejin Lee

Yejin Lee

Auto-generated profile, based on publicly available information

Yejin Lee

Meta, Menlo Park, CA, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2022
Verified
Conference Paper
Closed access
YLYejin Lee
Yejin Lee
HCHyunji Choi
Hyunji Choi
SMSunhong Min
Sunhong Min
HLHyunseung Lee
Hyunseung Lee
SBSangwon Beak
Sangwon Beak
THTae Jun Ham
Tae Jun Ham
Similarity search or nearest neighbor search is a task of retrieving a set of vectors in the (vector) database that are most similar to the provided query vector. It has been a key kernel for many applications for a long time. However, it is becoming especially more important in recent days as modern neural networks and machine learning models represent the semantics of images, videos, and documents as high-dimensional vectors called embeddings. Finding a set of similar embeddings for the provided query embedding is now the critical operation for modern recommender systems and semantic search engines. Since exhaustively searching for the most similar vectors out of billion vectors is such a prohibitive task, approximate nearest neighbor search (ANNS) is often utilized in many real-world use cases. Unfortunately, we find that utilizing the server-class CPUs and GPUs for the ANNS task leads to suboptimal performance and energy efficiency. To address such limitations, we propose a specialized architecture named ANNA (Approximate Nearest Neighbor search Accelerator), which is compatible with state-of-the-art ANNS algorithms such as Google ScaNN and Facebook Faiss. By combining the benefits of a specialized dataflow pipeline and efficient data reuse, ANNA achieves multiple orders of magnitude higher energy efficiency, 2.3-61.6× higher throughput, and 4.3-82.1× lower latency than the conventional CPU or GPU for both million- and billion-scale datasets.

17 April 2021
Verified
Conference Paper
Open access
YLYejin Lee
Yejin Lee
SSSeong Hoon Seo
Seong Hoon Seo
HCHyunji Choi
Hyunji Choi
HSHyoung Uk Sul
Hyoung Uk Sul
SKSoosung Kim
Soosung Kim
THTae Jun Ham
Tae Jun Ham
Deep neural networks (DNNs) with embedding layers are widely adopted to capture complex relationships among entities within a dataset. Embedding layers aggregate multiple embeddings — a dense vector used to represent the complicated nature of a data feature— into a single embedding; such operation is called embedding reduction. Embedding reduction spends a significant portion of its runtime on reading embeddings from memory and thus is known to be heavily memory-bandwidth-bound. Recent works attempt to accelerate this critical operation, but they often require either hardware modifications or emerging memory technologies, which makes it hardly deployable on commodity hardware. Thus, we propose MERCI, Memoization for Embedding Reduction with ClusterIng, a novel memoization framework for efficient embedding reduction. MERCI provides a mechanism for memoizing partial aggregation of correlated embeddings and retrieving the memoized partial result at a low cost. MERCI substantially reduces the number of memory accesses by 44% (29%), leading to 102% (74%) throughput improvement on real machines and 40.2% (28.6%) energy savings at the expense of 8×(1×) additional memory usage.

8 August 2025 in IEEE Micro
Verified
Journal Article
Closed access
YLYejin Lee
Yejin Lee
AGAlicia Golden
Alicia Golden
ASAnna Sun
Anna Sun
BHBasil Hosmer
Basil Hosmer
BABilge Acun
Bilge Acun
CWCarole-Jean Wu
Carole-Jean Wu
Generative artificial intelligence (AI) technology is revolutionizing the computing industry, posing new system design and optimization opportunities. In particular, AI’s ability to understand and respond in multiple modalities comes with significant system resource demands. To sustainably scale generative AI capabilities to billions of users in the world, inference must be fast and efficient. This paper pinpoints key system design and optimization opportunities by characterizing a family of emerging multi-modal generation models on real systems. Auto-regressive token generation is a critical latency performance bottleneck, typically dominated by GPU idle time. In addition to memory-intensive attention across the generative AI models, linear operations constitute significant inference latency due to the feed forward networks in Transformer-based models. We demonstrate that state-of-the-art optimization levers, spanning from applications to system software and hardware, set a 3.88× better baseline.