SoK: On Finding Common Ground in Loss Landscapes Using Deep Model Merging Techniques

• URL: http://arxiv.org/abs/2410.12927v1
• Date: Wed, 16 Oct 2024 18:14:05 GMT
• Title: SoK: On Finding Common Ground in Loss Landscapes Using Deep Model Merging Techniques
• Authors: Arham Khan, Todd Nief, Nathaniel Hudson, Mansi Sakarvadia, Daniel Grzenda, Aswathy Ajith, Jordan Pettyjohn, Kyle Chard, Ian Foster,
• Abstract summary: We present a novel taxonomy of model merging techniques organized by their core algorithmic principles. We distill repeated empirical observations from the literature in these fields into characterizations of four major aspects of loss landscape geometry.
• Score: 4.013324399289249
• License:
• Abstract: Understanding neural networks is crucial to creating reliable and trustworthy deep learning models. Most contemporary research in interpretability analyzes just one model at a time via causal intervention or activation analysis. Yet despite successes, these methods leave significant gaps in our understanding of the training behaviors of neural networks, how their inner representations emerge, and how we can predictably associate model components with task-specific behaviors. Seeking new insights from work in related fields, here we survey literature in the field of model merging, a field that aims to combine the abilities of various neural networks by merging their parameters and identifying task-specific model components in the process. We analyze the model merging literature through the lens of loss landscape geometry, an approach that enables us to connect observations from empirical studies on interpretability, security, model merging, and loss landscape analysis to phenomena that govern neural network training and the emergence of their inner representations. To systematize knowledge in this area, we present a novel taxonomy of model merging techniques organized by their core algorithmic principles. Additionally, we distill repeated empirical observations from the literature in these fields into characterizations of four major aspects of loss landscape geometry: mode convexity, determinism, directedness, and connectivity. We argue that by improving our understanding of the principles underlying model merging and loss landscape geometry, this work contributes to the goal of ensuring secure and trustworthy machine learning in practice.

Related papers

• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• Dynamics of Meta-learning Representation in the Teacher-student Scenario [8.099691748821114]
  Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. We investigate the meta-learning dynamics of the non-linear two-layer neural networks trained on streaming tasks in the teach-student scenario.
  arXiv  Detail & Related papers  (2024-08-22T16:59:32Z)
• Automatic Discovery of Visual Circuits [66.99553804855931]
  We explore scalable methods for extracting the subgraph of a vision model's computational graph that underlies recognition of a specific visual concept. We find that our approach extracts circuits that causally affect model output, and that editing these circuits can defend large pretrained models from adversarial attacks.
  arXiv  Detail & Related papers  (2024-04-22T17:00:57Z)
• Demolition and Reinforcement of Memories in Spin-Glass-like Neural Networks [0.0]
  The aim of this thesis is to understand the effectiveness of Unlearning in both associative memory models and generative models. The selection of structured data enables an associative memory model to retrieve concepts as attractors of a neural dynamics with considerable basins of attraction. A novel regularization technique for Boltzmann Machines is presented, proving to outperform previously developed methods in learning hidden probability distributions from data-sets.
  arXiv  Detail & Related papers  (2024-03-04T23:12:42Z)
• Experimental Observations of the Topology of Convolutional Neural Network Activations [2.4235626091331737]
  Topological data analysis provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture. In this paper, we apply cutting edge techniques from TDA with the goal of gaining insight into the interpretability of convolutional neural networks used for image classification.
  arXiv  Detail & Related papers  (2022-12-01T02:05:44Z)
• The Neural Race Reduction: Dynamics of Abstraction in Gated Networks [12.130628846129973]
  We introduce the Gated Deep Linear Network framework that schematizes how pathways of information flow impact learning dynamics. We derive an exact reduction and, for certain cases, exact solutions to the dynamics of learning. Our work gives rise to general hypotheses relating neural architecture to learning and provides a mathematical approach towards understanding the design of more complex architectures.
  arXiv  Detail & Related papers  (2022-07-21T12:01:03Z)
• Temporal Relevance Analysis for Video Action Models [70.39411261685963]
  We first propose a new approach to quantify the temporal relationships between frames captured by CNN-based action models. We then conduct comprehensive experiments and in-depth analysis to provide a better understanding of how temporal modeling is affected.
  arXiv  Detail & Related papers  (2022-04-25T19:06:48Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty [91.0564497403256]
  We present a novel framework that involves probabilistic fusion between the two families of predictions during network training. Our network features a self-attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences. We propose motion parmeterizations suitable for learning and show that our method achieves state-of-the-art performance on the challenging DeMoN and ScanNet datasets.
  arXiv  Detail & Related papers  (2021-04-16T17:59:06Z)
• Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles [69.9674326582747]
  This paper presents a visual framework to investigate neural network models subjected to adversarial examples. We show how observing these elements can quickly pinpoint exploited areas in a model.
  arXiv  Detail & Related papers  (2021-03-18T13:04:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.