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: http://creativecommons.org/licenses/by/4.0/
• 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

• Evaluating Loss Landscapes from a Topology Perspective [43.25939653609482]
  We characterize the underlying shape (or topology) of loss landscapes, quantifying the topology to reveal new insights about neural networks. To relate our findings to the machine learning (ML) literature, we compute simple performance metrics. We show how quantifying the shape of loss landscapes can provide new insights into model performance and learning dynamics.
  arXiv  Detail & Related papers  (2024-11-14T20:46:26Z)
• 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)
• Studying the Impact of Latent Representations in Implicit Neural Networks for Scientific Continuous Field Reconstruction [8.94539107276733]
  We present a novel model called MMGN (Multiplicative and Modulated Gabor Network) with implicit neural networks. We design additional studies leveraging explainability methods to complement the previous experiments and further enhance the understanding of latent representations generated by the model.
  arXiv  Detail & Related papers  (2024-04-09T16:07:35Z)
• A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes [49.32130498861987]
  We study the case of non-differentiable activation functions, such as ReLU. Two recent works introduced a geometric framework to study neural networks. We illustrate our findings with some numerical experiments on classification of images and thermodynamic problems.
  arXiv  Detail & Related papers  (2024-04-09T08:11:46Z)
• 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)
• Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
  Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
  arXiv  Detail & Related papers  (2023-07-25T17:59:18Z)
• 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)
• Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds [8.67467876089153]
  We present a new approach to studying such representations inspired by the idea of a frame on the tangent bundle of a manifold. Our construction, which we call a neural frame, is formed by assembling a set of vectors representing specific types of perturbations of a data point. Using neural frames, we make observations about the way that models process, layer-by-layer, specific modes of variation within a small neighborhood of a datapoint.
  arXiv  Detail & Related papers  (2022-11-19T01:48:19Z)
• 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)
• Geometric and Topological Inference for Deep Representations of Complex Networks [13.173307471333619]
  We present a class of statistics that emphasize the topology as well as the geometry of representations. We evaluate these statistics in terms of the sensitivity and specificity that they afford when used for model selection. These new methods enable brain and computer scientists to visualize the dynamic representational transformations learned by brains and models.
  arXiv  Detail & Related papers  (2022-03-10T17:14:14Z)
• 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)
• Extracting Global Dynamics of Loss Landscape in Deep Learning Models [0.0]
  We present a toolkit for the Dynamical Organization Of Deep Learning Loss Landscapes, or DOODL3. DOODL3 formulates the training of neural networks as a dynamical system, analyzes the learning process, and presents an interpretable global view of trajectories in the loss landscape.
  arXiv  Detail & Related papers  (2021-06-14T18:07:05Z)
• 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.