The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks

• URL: http://arxiv.org/abs/2405.10928v2
• Date: Mon, 20 May 2024 16:34:37 GMT
• Title: The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
• Authors: Lucius Bushnaq, Stefan Heimersheim, Nicholas Goldowsky-Dill, Dan Braun, Jake Mendel, Kaarel Hänni, Avery Griffin, Jörn Stöhler, Magdalena Wache, Marius Hobbhahn,
• Abstract summary: Local Interaction Basis aims to identify computational features by removing irrelevant activations and interactions. We evaluate the effectiveness of LIB on modular addition and CIFAR-10 models. We conclude that LIB is a promising theory-driven approach for analyzing neural networks, but in its current form is not applicable to large language models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mechanistic interpretability aims to understand the behavior of neural networks by reverse-engineering their internal computations. However, current methods struggle to find clear interpretations of neural network activations because a decomposition of activations into computational features is missing. Individual neurons or model components do not cleanly correspond to distinct features or functions. We present a novel interpretability method that aims to overcome this limitation by transforming the activations of the network into a new basis - the Local Interaction Basis (LIB). LIB aims to identify computational features by removing irrelevant activations and interactions. Our method drops irrelevant activation directions and aligns the basis with the singular vectors of the Jacobian matrix between adjacent layers. It also scales features based on their importance for downstream computation, producing an interaction graph that shows all computationally-relevant features and interactions in a model. We evaluate the effectiveness of LIB on modular addition and CIFAR-10 models, finding that it identifies more computationally-relevant features that interact more sparsely, compared to principal component analysis. However, LIB does not yield substantial improvements in interpretability or interaction sparsity when applied to language models. We conclude that LIB is a promising theory-driven approach for analyzing neural networks, but in its current form is not applicable to large language models.

Related papers

• Discovering Chunks in Neural Embeddings for Interpretability [53.80157905839065]
  We propose leveraging the principle of chunking to interpret artificial neural population activities. We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificial sequences with imposed regularities. We identify similar recurring embedding states corresponding to concepts in the input, with perturbations to these states activating or inhibiting the associated concepts.
  arXiv  Detail & Related papers  (2025-02-03T20:30:46Z)
• Efficient and Interpretable Neural Networks Using Complex Lehmer Transform [11.095723123836965]
  We propose an efficient and interpretable neural network with a novel activation function called the weighted Lehmer transform. We analyze the mathematical properties of both real-valued and complex-valued Lehmer activation units. Empirical evaluations demonstrate that our proposed neural network achieves competitive accuracy on benchmark datasets.
  arXiv  Detail & Related papers  (2025-01-25T14:08:30Z)
• Learning local discrete features in explainable-by-design convolutional neural networks [0.0]
  We introduce an explainable-by-design convolutional neural network (CNN) based on the lateral inhibition mechanism. The model consists of the predictor, that is a high-accuracy CNN with residual or dense skip connections. By collecting observations and directly calculating probabilities, we can explain causal relationships between motifs of adjacent levels.
  arXiv  Detail & Related papers  (2024-10-31T18:39:41Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• Seeking Interpretability and Explainability in Binary Activated Neural Networks [2.828173677501078]
  We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks. We present an approach based on the efficient computation of SHAP values for quantifying the relative importance of the features, hidden neurons and even weights.
  arXiv  Detail & Related papers  (2022-09-07T20:11:17Z)
• Modeling Implicit Bias with Fuzzy Cognitive Maps [0.0]
  This paper presents a Fuzzy Cognitive Map model to quantify implicit bias in structured datasets. We introduce a new reasoning mechanism equipped with a normalization-like transfer function that prevents neurons from saturating.
  arXiv  Detail & Related papers  (2021-12-23T17:04:12Z)
• PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations [2.047424180164312]
  We study the expectation of a probabilistic neural network as a predictor by itself, focusing on the aggregation of binary activated neural networks with normal distributions over real-valued weights. We show that the exact computation remains tractable for deep but narrow neural networks, thanks to a dynamic programming approach.
  arXiv  Detail & Related papers  (2021-10-28T14:11:07Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Measuring Model Complexity of Neural Networks with Curve Activation Functions [100.98319505253797]
  We propose the linear approximation neural network (LANN) to approximate a given deep model with curve activation function. We experimentally explore the training process of neural networks and detect overfitting. We find that the $L1$ and $L2$ regularizations suppress the increase of model complexity.
  arXiv  Detail & Related papers  (2020-06-16T07:38:06Z)

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.