Learning explanations that are hard to vary
- URL: http://arxiv.org/abs/2009.00329v3
- Date: Sat, 24 Oct 2020 11:32:18 GMT
- Title: Learning explanations that are hard to vary
- Authors: Giambattista Parascandolo, Alexander Neitz, Antonio Orvieto, Luigi
Gresele, Bernhard Sch\"olkopf
- Abstract summary: We show that averaging across examples can favor memorization and patchwork' solutions that sew together different strategies.
We then propose and experimentally validate a simple alternative algorithm based on a logical AND.
- Score: 75.30552491694066
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we investigate the principle that `good explanations are hard
to vary' in the context of deep learning. We show that averaging gradients
across examples -- akin to a logical OR of patterns -- can favor memorization
and `patchwork' solutions that sew together different strategies, instead of
identifying invariances. To inspect this, we first formalize a notion of
consistency for minima of the loss surface, which measures to what extent a
minimum appears only when examples are pooled. We then propose and
experimentally validate a simple alternative algorithm based on a logical AND,
that focuses on invariances and prevents memorization in a set of real-world
tasks. Finally, using a synthetic dataset with a clear distinction between
invariant and spurious mechanisms, we dissect learning signals and compare this
approach to well-established regularizers.
Related papers
- A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment
for Imbalanced Learning [129.63326990812234]
We propose a technique named data-dependent contraction to capture how modified losses handle different classes.
On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment.
arXiv Detail & Related papers (2023-10-07T09:15:08Z) - Trade-off Between Efficiency and Consistency for Removal-based
Explanations [12.338207007436566]
We establish the Impossible Trinity Theorem, which posits that interpretability, efficiency, and consistency cannot hold simultaneously.
Recognizing that the attainment of an ideal explanation remains elusive, we propose the utilization of interpretation error as a metric to gauge inefficiencies and inconsistencies.
Our empirical findings indicate that the proposed methods achieve a substantial reduction in interpretation error, up to 31.8 times lower when compared to alternative techniques.
arXiv Detail & Related papers (2022-10-31T15:56:39Z) - Resolving label uncertainty with implicit posterior models [71.62113762278963]
We propose a method for jointly inferring labels across a collection of data samples.
By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs.
arXiv Detail & Related papers (2022-02-28T18:09:44Z) - Label-Descriptive Patterns and their Application to Characterizing
Classification Errors [31.272875287136426]
State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless.
Characterizing these errors in easily interpretable terms gives insight into whether a model is prone to making systematic errors, but also gives a way to act and improve the model.
In this paper we propose a method that allows us to do so for arbitrary classifiers by mining a small set of patterns that together succinctly describe the input data that is partitioned according to correctness of prediction.
arXiv Detail & Related papers (2021-10-18T19:42:21Z) - A Low Rank Promoting Prior for Unsupervised Contrastive Learning [108.91406719395417]
We construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning.
Our hypothesis explicitly requires that all the samples belonging to the same instance class lie on the same subspace with small dimension.
Empirical evidences show that the proposed algorithm clearly surpasses the state-of-the-art approaches on multiple benchmarks.
arXiv Detail & Related papers (2021-08-05T15:58:25Z) - Learning the Truth From Only One Side of the Story [58.65439277460011]
We focus on generalized linear models and show that without adjusting for this sampling bias, the model may converge suboptimally or even fail to converge to the optimal solution.
We propose an adaptive approach that comes with theoretical guarantees and show that it outperforms several existing methods empirically.
arXiv Detail & Related papers (2020-06-08T18:20:28Z) - Sparse Methods for Automatic Relevance Determination [0.0]
We first review automatic relevance determination (ARD) and analytically demonstrate the need to additional regularization or thresholding to achieve sparse models.
We then discuss two classes of methods, regularization based and thresholding based, which build on ARD to learn parsimonious solutions to linear problems.
arXiv Detail & Related papers (2020-05-18T14:08:49Z) - Learning What Makes a Difference from Counterfactual Examples and
Gradient Supervision [57.14468881854616]
We propose an auxiliary training objective that improves the generalization capabilities of neural networks.
We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task.
Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
arXiv Detail & Related papers (2020-04-20T02:47:49Z)
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.