RELAX: Representation Learning Explainability
- URL: http://arxiv.org/abs/2112.10161v1
- Date: Sun, 19 Dec 2021 14:51:31 GMT
- Title: RELAX: Representation Learning Explainability
- Authors: Kristoffer K. Wickstr{\o}m, Daniel J. Trosten, Sigurd L{\o}kse, Karl
{\O}yvind Mikalsen, Michael C. Kampffmeyer, Robert Jenssen
- Abstract summary: We propose RELAX, which is the first approach for attribution-based explanations of representations.
ReLAX explains representations by measuring similarities in the representation space between an input and masked out versions of itself.
We provide theoretical interpretations of RELAX and conduct a novel analysis of feature extractors trained using supervised and unsupervised learning.
- Score: 10.831313203043514
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Despite the significant improvements that representation learning via
self-supervision has led to when learning from unlabeled data, no methods exist
that explain what influences the learned representation. We address this need
through our proposed approach, RELAX, which is the first approach for
attribution-based explanations of representations. Our approach can also model
the uncertainty in its explanations, which is essential to produce trustworthy
explanations. RELAX explains representations by measuring similarities in the
representation space between an input and masked out versions of itself,
providing intuitive explanations and significantly outperforming the
gradient-based baseline. We provide theoretical interpretations of RELAX and
conduct a novel analysis of feature extractors trained using supervised and
unsupervised learning, providing insights into different learning strategies.
Finally, we illustrate the usability of RELAX in multi-view clustering and
highlight that incorporating uncertainty can be essential for providing
low-complexity explanations, taking a crucial step towards explaining
representations.
Related papers
- A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels.
We present a generative latent variable model for self-supervised learning.
We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
arXiv Detail & Related papers (2024-02-02T13:31:17Z) - Specify Robust Causal Representation from Mixed Observations [35.387451486213344]
Learning representations purely from observations concerns the problem of learning a low-dimensional, compact representation which is beneficial to prediction models.
We develop a learning method to learn such representation from observational data by regularizing the learning procedure with mutual information measures.
We theoretically and empirically show that the models trained with the learned causal representations are more robust under adversarial attacks and distribution shifts.
arXiv Detail & Related papers (2023-10-21T02:18:35Z) - Understanding Self-Supervised Learning of Speech Representation via
Invariance and Redundancy Reduction [0.45060992929802207]
Self-supervised learning (SSL) has emerged as a promising paradigm for learning flexible speech representations from unlabeled data.
This study provides an empirical analysis of Barlow Twins (BT), an SSL technique inspired by theories of redundancy reduction in human perception.
arXiv Detail & Related papers (2023-09-07T10:23:59Z) - Explaining Explainability: Towards Deeper Actionable Insights into Deep
Learning through Second-order Explainability [70.60433013657693]
Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level.
We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
arXiv Detail & Related papers (2023-06-14T23:24:01Z) - Counterfactuals of Counterfactuals: a back-translation-inspired approach
to analyse counterfactual editors [3.4253416336476246]
We focus on the analysis of counterfactual, contrastive explanations.
We propose a new back translation-inspired evaluation methodology.
We show that by iteratively feeding the counterfactual to the explainer we can obtain valuable insights into the behaviour of both the predictor and the explainer models.
arXiv Detail & Related papers (2023-05-26T16:04:28Z) - Explaining, Evaluating and Enhancing Neural Networks' Learned
Representations [2.1485350418225244]
We show how explainability can be an aid, rather than an obstacle, towards better and more efficient representations.
We employ such attributions to define two novel scores for evaluating the informativeness and the disentanglement of latent embeddings.
We show that adopting our proposed scores as constraints during the training of a representation learning task improves the downstream performance of the model.
arXiv Detail & Related papers (2022-02-18T19:00:01Z) - A Free Lunch from the Noise: Provable and Practical Exploration for
Representation Learning [55.048010996144036]
We show that under some noise assumption, we can obtain the linear spectral feature of its corresponding Markov transition operator in closed-form for free.
We propose Spectral Dynamics Embedding (SPEDE), which breaks the trade-off and completes optimistic exploration for representation learning by exploiting the structure of the noise.
arXiv Detail & Related papers (2021-11-22T19:24:57Z) - Desiderata for Representation Learning: A Causal Perspective [104.3711759578494]
We take a causal perspective on representation learning, formalizing non-spuriousness and efficiency (in supervised representation learning) and disentanglement (in unsupervised representation learning)
This yields computable metrics that can be used to assess the degree to which representations satisfy the desiderata of interest and learn non-spurious and disentangled representations from single observational datasets.
arXiv Detail & Related papers (2021-09-08T17:33:54Z) - Explainable Recommender Systems via Resolving Learning Representations [57.24565012731325]
Explanations could help improve user experience and discover system defects.
We propose a novel explainable recommendation model through improving the transparency of the representation learning process.
arXiv Detail & Related papers (2020-08-21T05:30:48Z) - Fairness by Learning Orthogonal Disentangled Representations [50.82638766862974]
We propose a novel disentanglement approach to invariant representation problem.
We enforce the meaningful representation to be agnostic to sensitive information by entropy.
The proposed approach is evaluated on five publicly available datasets.
arXiv Detail & Related papers (2020-03-12T11:09:15Z)
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.