Know2Vec: A Black-Box Proxy for Neural Network Retrieval

Authors: Zhuoyi Shang, Yanwei Liu, Jinxia Liu, Xiaoyan Gu, Ying Ding, Xiangyang Ji

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that our Know2Vec achieves superior retrieval accuracy against the state-of-the-art methods in diverse neural network retrieval tasks. Experiments We compare our Know2Vec with several state-of-the-art methods in two scenarios: NNR and SF-MTE.
Researcher Affiliation Academia 1Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China 2School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China 3Key Laboratory of Cyberspace Security Defense, Beijing, China 4College of Information and Intelligence Engineering, Zhejiang Wanli University, Ningbo, China 5Tsinghua University, Beijing, China EMAIL, EMAIL, EMAIL, EMAIL
Pseudocode No The paper describes methods and formulas but does not include a clearly labeled pseudocode or algorithm block.
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it include a specific repository link or an explicit code release statement.
Open Datasets Yes For example, a model with numerical knowledge would find it easier to complete the MNIST(Deng 2012) classification task... The evaluation experiment is carried on a modified model-hub created from Kaggle1 with diverse real-world datasets/models... We evaluate various methods on 4 different downstream tasks, Aircraft(Maji et al. 2013) and DTD(Cimpoi et al. 2014) for classification, UTKFace (Zhang, Song, and Qi 2017) and d Sprites(Matthey et al. 2017) for regression. 1https://www.kaggle.com/
Dataset Splits No The paper uses various datasets but does not explicitly provide details about training/test/validation splits (e.g., percentages, sample counts, or specific split files) for reproducing the experiments.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions using a bidirectional Long Short Term Memory(LSTM)(Yu et al. 2019) network but does not provide specific version numbers for any software, libraries, or dependencies used in the experiments.
Experiment Setup Yes where α is a is a constant parameter to balance the different losses, and it is set to 1 in our experiment. For fairness, we fine-tuned the model generated from LLMs for 500 steps, as LLMs typically generate neural network rather than select them. We characterize the knowledge consistency with cosine similarity incorporating a margin of 0.4.