On the importance of single directions for generalization

19 March 2018

Papers citing "On the importance of single directions for generalization"

50 / 181 papers shown

Title
Studying Small Language Models with Susceptibilities Garrett Baker George Wang Jesse Hoogland Daniel Murfet AAML 78 1 0 25 Apr 2025
Early Stopping Against Label Noise Without Validation Data Suqin Yuan Lei Feng Tongliang Liu NoLa 104 16 0 11 Feb 2025
FedTLU: Federated Learning with Targeted Layer Updates Jong-Ik Park Carlee Joe-Wong FedML 84 0 0 28 Jan 2025
Dimensions underlying the representational alignment of deep neural networks with humans F. Mahner Lukas Muttenthaler Umut Güçlü M. Hebart 48 4 0 28 Jan 2025
On the uncertainty principle of neural networks Jun-Jie Zhang Dong-xiao Zhang Jian-Nan Chen L. Pang Deyu Meng 57 2 0 17 Jan 2025
Representation in large language models Cameron C. Yetman 41 1 0 03 Jan 2025
Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization Junlin He Jinxiao Du Susu Xu Wei Ma 26 0 0 01 Nov 2024
The Propensity for Density in Feed-forward Models Nandi Schoots Alex Jackson Ali Kholmovaia Peter McBurney Murray Shanahan CVBM 26 0 0 18 Oct 2024
Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient George Wang Jesse Hoogland Stan van Wingerden Zach Furman Daniel Murfet OffRL 36 7 0 03 Oct 2024
Addressing Data Heterogeneity in Federated Learning with Adaptive Normalization-Free Feature Recalibration Vasilis Siomos Sergio Naval Marimont Jonathan Passerat-Palmbach G. Tarroni 32 0 0 02 Oct 2024
DynFrs: An Efficient Framework for Machine Unlearning in Random Forest Shurong Wang Zhuoyang Shen Xinbao Qiao Tongning Zhang Meng Zhang MU 26 0 0 02 Oct 2024
Localizing Memorization in SSL Vision Encoders Wenhao Wang Adam Dziedzic Michael Backes Franziska Boenisch 34 2 0 27 Sep 2024
Linking in Style: Understanding learned features in deep learning models Maren H. Wehrheim Pamela Osuna-Vargas Matthias Kaschube GAN 31 0 0 25 Sep 2024
Y-Drop: A Conductance based Dropout for fully connected layers Efthymios Georgiou Georgios Paraskevopoulos Alexandros Potamianos 13 0 0 11 Sep 2024
The Quest for the Right Mediator: A History, Survey, and Theoretical Grounding of Causal Interpretability Aaron Mueller Jannik Brinkmann Millicent Li Samuel Marks Koyena Pal ... Arnab Sen Sharma Jiuding Sun Eric Todd David Bau Yonatan Belinkov CML 52 18 0 02 Aug 2024
Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks Zhicheng Cai Hao Zhu Qiu Shen Xinran Wang Xun Cao 41 0 0 25 Jul 2024
Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation Heng Xu Tianqing Zhu Lefeng Zhang Wanlei Zhou Philip S. Yu FedML MU 35 5 0 18 Jun 2024
Towards Efficient Target-Level Machine Unlearning Based on Essential Graph Heng Xu Tianqing Zhu Lefeng Zhang Wanlei Zhou Wei Zhao MU 35 1 0 16 Jun 2024
Feature contamination: Neural networks learn uncorrelated features and fail to generalize Tianren Zhang Chujie Zhao Guanyu Chen Yizhou Jiang Feng Chen OOD MLT OODD 77 3 0 05 Jun 2024
Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks Jun-Jie Zhang Deyu Meng AAML 17 3 0 16 Feb 2024
CAManim: Animating end-to-end network activation maps Emily Kaczmarek Olivier X. Miguel Alexa C. Bowie R. Ducharme Alysha L. J. Dingwall-Harvey S. Hawken Christine M. Armour Mark C. Walker Kevin Dick HAI 29 1 0 19 Dec 2023
Artificial Neural Nets and the Representation of Human Concepts Timo Freiesleben NAI 24 1 0 08 Dec 2023
Soft Matching Distance: A metric on neural representations that captures single-neuron tuning Meenakshi Khosla Alex H. Williams 17 12 0 16 Nov 2023
Probing clustering in neural network representations Thao Nguyen Simon Kornblith 32 1 0 14 Nov 2023
To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets Darshil Doshi Aritra Das Tianyu He Andrey Gromov OOD 34 6 0 19 Oct 2023
Identifying Interpretable Visual Features in Artificial and Biological Neural Systems David A. Klindt Sophia Sanborn Francisco Acosta Frédéric Poitevin Nina Miolane MILM FAtt 44 7 0 17 Oct 2023
Automated Natural Language Explanation of Deep Visual Neurons with Large Models Chenxu Zhao Wei Qian Yucheng Shi Mengdi Huai Ninghao Liu 29 2 0 16 Oct 2023
The Hydra Effect: Emergent Self-repair in Language Model Computations Tom McGrath Matthew Rahtz János Kramár Vladimir Mikulik Shane Legg MILM LRM 28 68 0 28 Jul 2023
Scale Alone Does not Improve Mechanistic Interpretability in Vision Models Roland S. Zimmermann Thomas Klein Wieland Brendel 31 13 0 11 Jul 2023
On the special role of class-selective neurons in early training Omkar Ranadive Nikhil Thakurdesai Ari S. Morcos Matthew L. Leavitt Stéphane Deny 17 2 0 27 May 2023
Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings Yihao Xue Ali Payani Yu Yang Baharan Mirzasoleiman VLM 26 4 0 23 May 2023
Explaining black box text modules in natural language with language models Chandan Singh Aliyah R. Hsu Richard Antonello Shailee Jain Alexander G. Huth Bin-Xia Yu Jianfeng Gao MILM 34 47 0 17 May 2023
Reduction of Class Activation Uncertainty with Background Information H. M. D. Kabir 26 9 0 05 May 2023
The Expressive Power of Tuning Only the Normalization Layers Angeliki Giannou Shashank Rajput Dimitris Papailiopoulos 24 8 0 15 Feb 2023
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders Sanghyun Woo Shoubhik Debnath Ronghang Hu Xinlei Chen Zhuang Liu In So Kweon Saining Xie SyDa 82 727 0 02 Jan 2023
Bio-Inspired, Task-Free Continual Learning through Activity Regularization Francesco Lassig Pau Vilimelis Aceituno M. Sorbaro Benjamin Grewe CLL 27 8 0 08 Dec 2022
ModelDiff: A Framework for Comparing Learning Algorithms Harshay Shah Sung Min Park Andrew Ilyas A. Madry SyDa 51 26 0 22 Nov 2022
On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning S. Takagi OffRL 18 7 0 17 Nov 2022
Finding Skill Neurons in Pre-trained Transformer-based Language Models Xiaozhi Wang Kaiyue Wen Zhengyan Zhang Lei Hou Zhiyuan Liu Juanzi Li MILM MoE 27 50 0 14 Nov 2022
Much Easier Said Than Done: Falsifying the Causal Relevance of Linear Decoding Methods L. Hayne Abhijit Suresh Hunar Jain Rahul Kumar R. M. Carter FAtt 35 1 0 08 Nov 2022
On the Algorithmic Stability and Generalization of Adaptive Optimization Methods Han Nguyen Hai Pham Sashank J. Reddi Barnabás Póczos ODL AI4CE 17 2 0 08 Nov 2022
Higher-order mutual information reveals synergistic sub-networks for multi-neuron importance Kenzo Clauw S. Stramaglia Daniele Marinazzo SSL FAtt 30 6 0 01 Nov 2022
Rethinking Normalization Methods in Federated Learning Zhixu Du Jingwei Sun Ang Li Pin-Yu Chen Jianyi Zhang H. Li Yiran Chen FedML 29 28 0 07 Oct 2022
Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networks Seokhyun Byun Won-Jo Lee FAtt 39 4 0 28 Sep 2022
Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks Tilman Raukur A. Ho Stephen Casper Dylan Hadfield-Menell AAML AI4CE 23 124 0 27 Jul 2022
Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations Lin Zhao Haixing Dai Zihao Wu Zhe Xiao Lu Zhang ... Xintao Hu Xi Jiang Sheng Li Dajiang Zhu Tianming Liu 33 7 0 22 Jun 2022
Batch Normalization Is Blind to the First and Second Derivatives of the Loss Zhanpeng Zhou Wen Shen Huixin Chen Ling Tang Quanshi Zhang 34 2 0 30 May 2022
Adversarial Parameter Attack on Deep Neural Networks Lijia Yu Yihan Wang Xiao-Shan Gao AAML 29 8 0 20 Mar 2022
Towards understanding deep learning with the natural clustering prior Simon Carbonnelle 18 0 0 15 Mar 2022
Testing the Tools of Systems Neuroscience on Artificial Neural Networks Grace W. Lindsay 22 4 0 14 Feb 2022