A survey on model compression for large language models
Abstract Large Language Models (LLMs) have transformed natural language processing
tasks successfully. Yet, their large size and high computational needs pose challenges for …
tasks successfully. Yet, their large size and high computational needs pose challenges for …
Efficient evaluation methods for neural architecture search: A survey
Neural Architecture Search (NAS) has received increasing attention because of its
exceptional merits in automating the design of Deep Neural Network (DNN) architectures …
exceptional merits in automating the design of Deep Neural Network (DNN) architectures …
Improving Differentiable Architecture Search via self-distillation
Abstract Differentiable Architecture Search (DARTS) is a simple yet efficient Neural
Architecture Search (NAS) method. During the search stage, DARTS trains a supernet by …
Architecture Search (NAS) method. During the search stage, DARTS trains a supernet by …
Flexible order aware sequential recommendation
Sequential recommendations can dynamically model user interests, which has great value
since users' interests may change rapidly with time. Traditional sequential recommendation …
since users' interests may change rapidly with time. Traditional sequential recommendation …
IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance
H He, L Liu, H Zhang, N Zheng - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Among existing Neural Architecture Search methods, DARTS is known for its efficiency and
simplicity. This approach applies continuous relaxation of network representation to …
simplicity. This approach applies continuous relaxation of network representation to …
Robust Neural Architecture Search
X Zhu, J Li, Y Liu, W Wang - arXiv preprint arXiv:2304.02845, 2023 - arxiv.org
Neural Architectures Search (NAS) becomes more and more popular over these years.
However, NAS-generated models tends to suffer greater vulnerability to various malicious …
However, NAS-generated models tends to suffer greater vulnerability to various malicious …
User Popularity Preference Aware Sequential Recommendation
In recommender systems, users' preferences for item popularity are diverse and dynamic,
which reveals the different items that users prefer. Therefore, identifying user popularity …
which reveals the different items that users prefer. Therefore, identifying user popularity …