An official website of the United States government
The performance of deep neural networks often deteriorates in out-of-distribution settings due to relying on easy-to-learn but unreliable spurious associations known as shortcuts. Recent work attempting to mitigate shortcut learning relies on a priori knowledge of what the shortcut is and requires a strict overlap assumption with respect to the shortcut and the labels. In this paper, we present a causally-motivated teacher-student framework that encourages invariance to all shortcuts by leveraging privileged mediation information. The Teaching Invariance using Privileged Mediation Information (TIPMI) framework distills knowledge from a counterfactually invariant teacher trained using privileged mediation information to a student predictor that uses non-privileged features. We analyze the theoretical properties of our proposed estimator, showing that TIPMI promotes invariance to multiple unknown shortcuts and has better finite-sample efficiency. We empirically verify our theoretical findings by showing that TIPMI outperforms several state-of-the-art methods on two vision datasets and one language dataset.
more »
« less
Causally motivated multi-shortcut identification & removal
For predictive models to provide reliable guidance in decision making processes, they are often required to be accurate and robust to distribution shifts. Shortcut learning–where a model relies on spurious correlations or shortcuts to predict the target label–undermines the robustness property, leading to models with poor out-of-distribution accuracy despite good in-distribution performance. Existing work on shortcut learning either assumes that the set of possible shortcuts is known a priori or is discoverable using interpretability methods such as saliency maps, which might not always be true. Instead, we propose a two step approach to (1) efficiently identify relevant shortcuts, and (2) leverage the identified shortcuts to build models that are robust to distribution shifts. Our approach relies on having access to a (possibly) high dimensional set of auxiliary labels at training time, some of which correspond to possible shortcuts. We show both theoretically and empirically that our approach is able to identify a sufficient set of shortcuts leading to more efficient predictors in finite samples.
more »
« less
- Award ID(s):
- 2153083
- PAR ID:
- 10386343
- Date Published:
- Journal Name:
- Advances in neural information processing systems
- ISSN:
- 1049-5258
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Deep neural networks are susceptible to shortcut learning, using simple features to achieve low training loss without discovering essential semantic structure. Contrary to prior belief, we show that generative models alone are not sufficient to prevent shortcut learning, despite an incentive to recover a more comprehensive representation of the data than discriminative approaches. However, we observe that shortcuts are preferentially encoded with minimal information, a fact that generative models can exploit to mitigate shortcut learning. In particular, we propose Chroma-VAE, a two-pronged approach where a VAE classifier is initially trained to isolate the shortcut in a small latent subspace, allowing a secondary classifier to be trained on the complementary, shortcut-free latent subspace. In addition to demonstrating the efficacy of Chroma-VAE on benchmark and real-world shortcut learning tasks, our work highlights the potential for manipulating the latent space of generative classifiers to isolate or interpret specific correlations.more » « less
-
During training, models can exploit spurious correlations as shortcuts, resulting in poor generalization performance when shortcuts do not persist. In this work, assuming access to a representation based on domain knowledge (i.e., known concepts) that is invariant to shortcuts, we aim to learn robust and accurate models from biased training data. In contrast to previous work, we do not rely solely on known concepts, but allow the model to also learn unknown concepts. We propose two approaches for mitigating shortcuts that incorporate domain knowledge, while accounting for potentially important yet unknown concepts. The first approach is two-staged. After fitting a model using known concepts, it accounts for the residual using unknown concepts. While flexible, we show that this approach is vulnerable when shortcuts are correlated with the unknown concepts. This limitation is addressed by our second approach that extends a recently proposed regularization penalty. Applied to two real-world datasets, we demonstrate that both approaches can successfully mitigate shortcut learning.more » « less
-
Interconnection network topology is critical for the overall performance of HPC systems. While many regular and irregular topologies have been proposed in the past, recent work has shown the promise of shortcut-augmented topologies that offer multi-fold reduction in network diameter and hop count over conventional topologies. However, the large number of possible shortcuts creates an enormous design space for this new type of topology, and existing approaches are extremely slow and do not find shortcuts that are globally optimal. In this paper, we propose an efficient heuristic approach, called EdgeCut, which generates high-quality shortcut-augmented topologies. EdgeCut can identify more globally useful shortcuts by making its considerations from the perspective of edges instead of vertices. An additional implementation is proposed that approximates the costly all-pair shortest paths calculation, thereby further speeding up the scheme. Quantitative comparisons over prior work show that the proposed approach achieves a 1982× reduction in search time while generating better or equivalent topologies in 94.9% of the evaluated cases.more » « less
-
Large language models (LLMs) demonstrate surprising capabilities, but we do not understand how they are implemented. One hypothesis suggests that these capabilities are primarily executed by small subnetworks within the LLM, known as circuits. Identifying these circuits is particularly useful in the context of building models that are robust to shortcut learning and distribution shifts. Identifying these shortcut encoding circuits allows us to "turn them off" by replacing their outputs with random values or zeros. Many papers have claimed to identify meaningful circuits in existing language models. In this paper, we focus on evaluating candidate circuits. Specifically, we formalize a set of criteria that a circuit is hypothesized to meet and develop a suite of hypothesis tests to evaluate how well circuits satisfy them. The criteria focus on the extent to which the LLM's behavior is preserved, the degree of localization of this behavior, and whether the circuit is minimal. We apply these tests to six circuits described in the research literature. We find that synthetic circuits -- circuits that are hard-coded in the model -- align with the idealized properties. Circuits discovered in Transformer models satisfy the criteria to varying degrees. To facilitate future empirical studies of circuits, we created the circuitry package, a wrapper around the TransformerLens library, which abstracts away lower-level manipulations of hooks and activations. The software is available at https://github.com/blei-lab/circuitry.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
