More Like this

1. The Risks of Invariant Risk Minimization

   Rosenfeld, Elan; Ravikumar, Pradeep; Risteski, Andrej (July 2021, International Conference on Learning Representations)

   null (Ed.)

   Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution generalization which assumes that some aspects of the data distribution vary across the training set but that the underlying causal mechanisms remain constant. Recently, Arjovsky et al. (2019) proposed Invariant Risk Minimization (IRM), an objective based on this idea for learning deep, invariant features of data which are a complex function of latent variables; many alternatives have subsequently been suggested. However, formal guarantees for all of these works are severely lacking. In this paper, we present the first analysis of classification under the IRM objective—as well as these recently proposed alternatives—under a fairly natural and general model. In the linear case, we give simple conditions under which the optimal solution succeeds or, more often, fails to recover the optimal invariant predictor. We furthermore present the very first results in the non-linear regime: we demonstrate that IRM can fail catastrophically unless the test data are sufficiently similar to the training distribution—this is precisely the issue that it was intended to solve. Thus, in this setting we find that IRM and its alternatives fundamentally do not improve over standard Empirical Risk Minimization. 

   more » « less
2. Does Invariant Risk Minimization Capture Invariance?

   Kamath, Pritish; Tangella, Akilesh; Sutherland, Danica; Srebro, Nathan (April 2021, Proceedings of Machine Learning Research)

   null (Ed.)

   We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture “natural” invariances, at least when used in its practical “linear” form, and even on very simple problems which directly follow the motivating examples for IRM. This can lead to worse generalization on new environments, even when compared to unconstrained ERM. The issue stems from a significant gap between the linear variant (as in their concrete method IRMv1) and the full non-linear IRM formulation. Additionally, even when capturing the “right” invariances, we show that it is possible for IRM to learn a sub-optimal predictor, due to the loss function not being invariant across environments. The issues arise even when measuring invariance on the population distributions, but are exacerbated by the fact that IRM is extremely fragile to sampling. 

   more » « less
3. Fairness and accuracy under domain generalization

   Thai-Hoang Pham; Xueru Zhang; Ping Zhang (February 2023, International Conference on Learning Representations (ICLR))

   As machine learning (ML) algorithms are increasingly used in high-stakes applications, concerns have arisen that they may be biased against certain social groups. Although many approaches have been proposed to make ML models fair, they typically rely on the assumption that data distributions in training and deployment are identical. Unfortunately, this is commonly violated in practice and a model that is fair during training may lead to an unexpected outcome during its deployment. Although the problem of designing robust ML models under dataset shifts has been widely studied, most existing works focus only on the transfer of accuracy. In this paper, we study the transfer of both fairness and accuracy under domain generalization where the data at test time may be sampled from never-before-seen domains. We first develop theoretical bounds on the unfairness and expected loss at deployment, and then derive sufficient conditions under which fairness and accuracy can be perfectly transferred via invariant representation learning. Guided by this, we design a learning algorithm such that fair ML models learned with training data still have high fairness and accuracy when deployment environments change. Experiments on real-world data validate the proposed algorithm. 

   more » « less
4. Unsupervised Adversarial Domain Adaptation in Wearable Physiological Sensing for Construction Workers’ Health Monitoring Using Photoplethysmography

   https://doi.org/10.1061/9780784485262.035  

   Gautam, Yogesh; Liu, Yizhi; Jebelli, Houtan (March 2024, Construction Research Congress 2024)

   Recent advancements in wearable physiological sensing and artificial intelligence have made some remarkable progress in workers’ health monitoring in construction sites. However, the scalable application is still challenging. One of the major complications for deployment has been the distribution shift observed in the physiological data obtained through sensors. This study develops a deep adversarial domain adaptation framework to adapt to out-of-distribution data(ODD) in the wearable physiological device based on photoplethysmography (PPG). The domain adaptation framework is developed and validated with reference to the heart rate predictor based on PPG. A heart rate predictor module comprising feature generating encoder and predictor isinitially trained with data from a given training domain. An unsupervised adversarial domain adaptation method is then implemented for the test domain. In the domain adaptation process, the encoder network is adapted to generate domain invariant features for the test domain using discriminator-based adversarial optimization. The results demonstrate that this approach can effectively accomplish domain adaptation, as evidenced by a 27.68% reduction in heart rate prediction error for the test domain. The proposed framework offers potential for scaled adaptation in the jobsite by addressing the ODD problem. 

   more » « less
5. Face Sketch Matching via Coupled Deep Transform Learning

   https://doi.org/10.1109/ICCV.2017.579  

   Nagpal, Shruti; Singh, Maneet; Singh, Richa; Vatsa, Mayank; Noore, Afzel; Majumdar, Angshul (October 2017, International Joint Conference on Biometrics (IJCB))

   Face sketch to digital image matching is an important challenge of face recognition that involves matching across different domains. Current research efforts have primarily focused on extracting domain invariant representations or learning a mapping from one domain to the other. In this research, we propose a novel transform learning based approach termed as DeepTransformer, which learns a transformation and mapping function between the features of two domains. The proposed formulation is independent of the input information and can be applied with any existing learned or hand-crafted feature. Since the mapping function is directional in nature, we propose two variants of DeepTransformer: (i) semi-coupled and (ii) symmetricallycoupled deep transform learning. This research also uses a novel IIIT-D Composite Sketch with Age (CSA) variations database which contains sketch images of 150 subjects along with age-separated digital photos. The performance of the proposed models is evaluated on a novel application of sketch-to-sketch matching, along with sketch-to-digital photo matching. Experimental results demonstrate the robustness of the proposed models in comparison to existing state-of-the-art sketch matching algorithms and a commercial face recognition system. 

   more » « less