Fetching the paper…
Reading the bibliography…
Influence functions (IFs) elucidate how training data changes model behavior.
An iteration method for the solution of the eigenvalue problem of linear differential and integral operators
Lanczos, C · 1950
Earlier work this paper cites.
The influence curve and its role in robust estimation
Hampel, F. R · 1974
Earlier work this paper cites.
Fast Exact Multiplication by the Hessian
Pearlmutter, B. A · 1994
Earlier work this paper cites.
Matrix algorithms
Stewart, G. W · 2001
Earlier work this paper cites.
Generalized inverses: theory and applications , volume 15
Ben-Israel, A. and Greville, T. N · 2003
Earlier work this paper cites.
Statistical Parametric Mapping: the Analysis of Functional Brain Images
Penny, W. D., Friston, K. J., Ashburner, J. T., Kiebel, S. J., and Nichols, T. E · 2011
Earlier work this paper cites.
Geometry of nonlinear least squares with applications to sloppy models and optimization
Transtrum, M. K., Machta, B. B., and Sethna, J. P · 2011
Earlier work this paper cites.
Nonlinear Programming , volume 4
Bertsekas, D · 2016
Earlier work this paper cites.
Network trimming: A data-driven neuron pruning approach towards efficient deep architectures
Hu, H., Peng, R., Tai, Y., and Tang, C · 2016
Earlier work this paper cites.
Second-order stochastic optimization for machine learning in linear time
Agarwal, N., Bullins, B., and Hazan, E · 2017
Earlier work this paper cites.
Understanding black-box predictions via influence functions
Koh, P. W. and Liang, P · 2017
Earlier work this paper cites.
Grad-cam: Visual explanations from deep networks via gradient-based localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D · 2017
Earlier work this paper cites.
The building blocks of interpretability
Olah, C., Satyanarayan, A., Johnson, I., Carter, S., Schubert, L., Ye, K., and Mordvintsev, A · 2018
Earlier work this paper cites.
The lottery ticket hypothesis: Finding sparse, trainable neural networks
Frankle, J. and Carbin, M · 2019
Cited alongside, same era.
On the accuracy of influence functions for measuring group effects
Koh, P. W., Ang, K.-S., Teo, H. H. K., and Liang, P · 2019
Cited alongside, same era.
Snip: Single-shot network pruning based on connection sensitivity
Lee, N., Ajanthan, T., and Torr, P. H · 2019
Cited alongside, same era.
Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., and Herrera, F · 2020
Cited alongside, same era.
Understanding the role of individual units in a deep neural network
Bau, D., Zhu, J.-Y., Strobelt, H., Lapedriza, A., Zhou, B., and Torralba, A · 2020
Cited alongside, same era.
Stronger data poisoning attacks break data sanitization defenses
Koh, P. W., Steinhardt, J., and Liang, P · 2022
Later among the works it cites.
Resolving training biases via influence-based data relabeling
Kong, S., Shen, Y., and Huang, L · 2022
Later among the works it cites.
Scaling up influence functions
Schioppa, A., Zablotskaia, P., Vilar, D., and Sokolov, A · 2022
Later among the works it cites.
PUMA: Performance unchanged model augmentation for training data removal
Wu, G., Hashemi, M., and Srinivasa, C · 2022
Later among the works it cites.
ProGen: Progressive zero-shot dataset generation via in-context feedback
Ye, J., Gao, J., Wu, Z., Feng, J., Yu, T., and Kong, L · 2022
Later among the works it cites.
‘AI pause’ open letter stokes fear and controversy
Anderson, M · 2023
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Lee, D., Park, H., Pham, T., and Yoo, C. D · 2020
Cited alongside, same era.
Picking winning tickets before training by preserving gradient flow
Wang, C., Zhang, G., and Grosse, R · 2020
Cited alongside, same era.
Influence functions in deep learning are fragile
Basu, S., Pope, P. E., and Feizi, S · 2021
Cited alongside, same era.
FastIF: Scalable influence functions for efficient model interpretation and debugging
Guo, H., Rajani, N., Hase, P., Bansal, M., and Xiong, C · 2021
Cited alongside, same era.
Membership inference attack using self influence functions, 2022
Cohen, G. and Giryes, R · 2022
Cited alongside, same era.
Partial label learning via label influence function
Gong, X., Yuan, D., and Bao, W · 2022
Cited alongside, same era.
Influence functions for sequence tagging models
Jain, S., Manjunatha, V., Wallace, B., and Nenkova, A · 2022
Cited alongside, same era.
Revisiting the fragility of influence functions
Epifano, J. R., Ramachandran, R. P., Masino, A. J., and Rasool, G · 2023
Closest in time.
Studying large language model generalization with influence functions, 2023
Grosse, R., Bae, J., Anil, C., Elhage, N., Tamkin, A., Tajdini, A., Steiner, B., Li, D., Durmus, E., Perez, E., Hubinger, E., Lukošiūtė, K., Nguyen, K., Joseph, N., McCandlish, S., Kaplan, J., and Bowman, S. R · 2023
Closest in time.
Gif: A general graph unlearning strategy via influence function
Wu, J., Yang, Y., Qian, Y., Sui, Y., Wang, X., and He, X · 2023
Closest in time.
Dataset pruning: Reducing training data by examining generalization influence
Yang, S., Xie, Z., Peng, H., Xu, M., Sun, M., and Li, P · 2023
Closest in time.
Few-shot unlearning by model inversion, 2023
Yoon, Y., Nam, J., Yun, H., Lee, J., Kim, D., and Ok, J · 2023
Closest in time.
Datainf: Efficiently estimating data influence in loRA-tuned LLMs and diffusion models
Kwon, Y., Wu, E., Wu, K., and Zou, J · 2024
Closest in time.