Authors:
(1) Sanchit Sinha, University of Virginia (sanchit@virginia.edu);
(2) Guangzhi Xiong, University of Virginia (hhu4zu@virginia.edu);
(3) Aidong Zhang, University of Virginia (aidong@virginia.edu). Table of Links Abstract and 1 Introduction 2 Related Work 3 Methodology and 3.1 Representative Concept Extraction 3.2 Self-supervised Contrastive Concept Learning 3.3 Prototype-based Concept Grounding 3.4 End-to-end Composite Training 4 Experiments and 4.1 Datasets and Networks 4.2 Hyperparameter Settings 4.3 Evaluation Metrics and 4.4 Generalization Results 4.5 Concept Fidelity and 4.6 Qualitative Visualization 5 Conclusion and References Appendix 4.3 Evaluation Metrics We consider the following evaluation metrics to evaluate each component of the concept discovery framework. • Generalization: We start by quantitatively evaluating the quality of concepts learned by measuring how well the learned concepts can generalize to new domains. To achieve this, we compare our proposed method against the aforementioned baselines on domain adaptation settings. • Concept Fidelity: To evaluate consistency in the learned concepts, we compute the intersection over union of the concept sets associated with for two data points xi and xj from same class as defined in Equation 10: 4.4 Genenralization Results Tables 2, 3, and 4 report the domain adaptation results on the OfficeHome, DomainNet, VisDA and the Digit datasets, respectively. The notation X→Y represents models trained on X as the source domain (with abundant data) and Y as the target domain (with limited data) and evaluated on the test set of domain Y . The best statistically significant accuracy is reported in bold. The last three rows in all the tables list the performance of the RCE framework, RCE trained with regularization (RCE+PCG), and RCE trained with both regularization and contrastive learning paradigm (RCE+PCG+CCL). Comparision with baselines. The first row in each table lists the performance of a standard Neural Network trained using the setting described in [Yu and Lin, 2023] (S+T). As a standard NN is not inherently explainable, we consider this setting as a baseline to understand the upper bound of the performance-explainability tradeoff. The second and third rows in each table lists the performance of SENN and DiSENN respectively. SENN performs worse than S+T setting in almost all settings, except in a handful of settings where the performance matches S+T. This is expected, as SENN is formulated as an overparameterized version of a standard NN with regularization. Recall that DiSENN replaces the autoencoder in SENN with a VAE, and as such is not generalizable to bigger datasets without domain engineering. DiSENN performs the worst among all approaches for all datasets due to poor VAE generalization. Recall that UnsupervisedCBM is an improved version of SENN architecture with a discriminator in addition to the aggregation function. In most cases, it performs slightly better than SENN and is at par with S+T. However, in particular cases in OfficeHome data (R→A) and DomainNet (S→P), UnsupCBM performs the best. We attribute this result to two factors: first, the Art (A) and Sketch (S) domains are significantly different from Real (R) and Picture (P) domains due to both of the former being hand-drawn while the latter being photographed as mentioned in [Yu and Lin, 2023]. Second, the use of a discriminator as proposed in UnsupervisedCBM helps enforce domain invariance in those particular cases. BotCL explicitly attempts to improve concept fidelity and applies contrastive learning to discover concepts. However, the contrastive loss formulation is rather basic and they never focuses on domain invariance. BotCL’s performance is similar to S+T for the most part except in OfficeHome data (C→A), where it just outperforms all other approaches. One possible reason is that Clipart domain is significantly less noisy, and hence basic transformations in BotCL work well. As the last row demonstrates, our proposed framework RCE+PCG+CCL outperforms all baselines on a vast majority of the settings across all four datasets and is comparable to SOTA baselines in the other settings. Ablation studies. We also report the performance corresponding to various components of our proposed approach. We observe that the performance of RCE is almost identical to SENN, which is expected as there is very weak regularization in both cases. In almost all cases, adding prototype-based grounding regularization (RCE+PCG) improves performance over RCE while models trained with both PCG regularization and contrastive learning (RCE+PCG+CCL) outperform all approaches on a vast majority of settings across all datasets. Note that the setting RCE+CCL is not reported, as it defeats the fundamental motivation of maintaining concept fidelity. Effect of the number of concepts and dimensions. We observe that there are no significant differences in performance over a varying number of concepts or dimensions. For all results reported, the number of concepts is set to a number of classes in the dataset, and their dimension is set to 1. For results on varying numbers of concepts and dimensions - refer to Appendix. 4.5 Concept Fidelity As the RCE framework is explicitly regularized with a concept fidelity regularizer and grounded using prototypes, we would expect high fidelity scores. Table 5 lists the fidelity scores for the aforementioned baselines and our proposed method. Fidelity scores are averaged for each domain when taken as a target (e.g. for the domain (A) in DomainNet, the score is an average of C→A, P→A and R→A). As expected, our method and BotCL, both with specific fidelity regularization outperform all other baseline approaches. Our method outperforms BotCL in most settings, except when the target domains are Art in DomainNet and Clipart in OfficHome due to significant domain dissonance. 4.6 Qualitative Visualization Domain Alignment. We consider the extent to which the models trained using both concept grounding and contrastive learning maintain concept consistency not only within the source domain but also across the target domain as well. To understand what discriminative information is captured by a particular concept, Figure 5 shows the most important prototypes selected from the training set of both the source and target domains corresponding to five randomly selected concepts. We observe that prototypes explaining each concept are visually similar. For more results, refer Appendix. Explanation using prototypes. For a given input sample, we also plot the prototypes associated with the highest activated concept, i.e., the important concept. Figure 6 shows the prototypes associated with the concepts most responsible for prediction (highest relevance scores). As can be seen, the prototypes possess distinct features, for eg., they capture the round face of an alarm clock. More results are reported in Appendix. This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Sanchit Sinha, University of Virginia (sanchit@virginia.edu); (2) Guangzhi Xiong, University of Virginia (hhu4zu@virginia.edu); (3) Aidong Zhang, University of Virginia (aidong@virginia.edu). Authors: Authors: (1) Sanchit Sinha, University of Virginia (sanchit@virginia.edu); (2) Guangzhi Xiong, University of Virginia (hhu4zu@virginia.edu); (3) Aidong Zhang, University of Virginia (aidong@virginia.edu). Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2 Related Work 2 Related Work 3 Methodology and 3.1 Representative Concept Extraction 3 Methodology and 3.1 Representative Concept Extraction 3.2 Self-supervised Contrastive Concept Learning 3.2 Self-supervised Contrastive Concept Learning 3.3 Prototype-based Concept Grounding 3.3 Prototype-based Concept Grounding 3.4 End-to-end Composite Training 3.4 End-to-end Composite Training 4 Experiments and 4.1 Datasets and Networks 4 Experiments and 4.1 Datasets and Networks 4.2 Hyperparameter Settings 4.2 Hyperparameter Settings 4.3 Evaluation Metrics and 4.4 Generalization Results 4.3 Evaluation Metrics and 4.4 Generalization Results 4.5 Concept Fidelity and 4.6 Qualitative Visualization 4.5 Concept Fidelity and 4.6 Qualitative Visualization 5 Conclusion and References 5 Conclusion and References Appendix Appendix 4.3 Evaluation Metrics We consider the following evaluation metrics to evaluate each component of the concept discovery framework. • Generalization : We start by quantitatively evaluating the quality of concepts learned by measuring how well the learned concepts can generalize to new domains. To achieve this, we compare our proposed method against the aforementioned baselines on domain adaptation settings. Generalization • Concept Fidelity: To evaluate consistency in the learned concepts, we compute the intersection over union of the concept sets associated with for two data points xi and xj from same class as defined in Equation 10: • Concept Fidelity: 4.4 Genenralization Results Tables 2, 3, and 4 report the domain adaptation results on the OfficeHome, DomainNet, VisDA and the Digit datasets, respectively. The notation X→Y represents models trained on X as the source domain (with abundant data) and Y as the target domain (with limited data) and evaluated on the test set of domain Y . The best statistically significant accuracy is reported in bold. The last three rows in all the tables list the performance of the RCE framework, RCE trained with regularization (RCE+PCG), and RCE trained with both regularization and contrastive learning paradigm (RCE+PCG+CCL) . RCE RCE (RCE+PCG), RCE (RCE+PCG+CCL) Comparision with baselines. The first row in each table lists the performance of a standard Neural Network trained using the setting described in [Yu and Lin, 2023] (S+T). As a standard NN is not inherently explainable, we consider this setting as a baseline to understand the upper bound of the performance-explainability tradeoff. Comparision with baselines. The second and third rows in each table lists the performance of SENN and DiSENN respectively. SENN performs worse than S+T setting in almost all settings, except in a handful of settings where the performance matches S+T. This is expected, as SENN is formulated as an overparameterized version of a standard NN with regularization. Recall that DiSENN replaces the autoencoder in SENN with a VAE, and as such is not generalizable to bigger datasets without domain engineering. DiSENN performs the worst among all approaches for all datasets due to poor VAE generalization. Recall that UnsupervisedCBM is an improved version of SENN architecture with a discriminator in addition to the aggregation function. In most cases, it performs slightly better than SENN and is at par with S+T. However, in particular cases in OfficeHome data (R→A) and DomainNet (S→P), UnsupCBM performs the best. We attribute this result to two factors: first, the Art (A) and Sketch (S) domains are significantly different from Real (R) and Picture (P) domains due to both of the former being hand-drawn while the latter being photographed as mentioned in [Yu and Lin, 2023]. Second, the use of a discriminator as proposed in UnsupervisedCBM helps enforce domain invariance in those particular cases. BotCL explicitly attempts to improve concept fidelity and applies contrastive learning to discover concepts. However, the contrastive loss formulation is rather basic and they never focuses on domain invariance. BotCL’s performance is similar to S+T for the most part except in OfficeHome data (C→A), where it just outperforms all other approaches. One possible reason is that Clipart domain is significantly less noisy, and hence basic transformations in BotCL work well. As the last row demonstrates, our proposed framework RCE+PCG+CCL outperforms all baselines on a vast majority of the settings across all four datasets and is comparable to SOTA baselines in the other settings. Ablation studies. We also report the performance corresponding to various components of our proposed approach. We observe that the performance of RCE is almost identical to SENN, which is expected as there is very weak regularization in both cases. In almost all cases, adding prototype-based grounding regularization (RCE+PCG) improves performance over RCE while models trained with both PCG regularization and contrastive learning (RCE+PCG+CCL) outperform all approaches on a vast majority of settings across all datasets. Note that the setting RCE+CCL is not reported, as it defeats the fundamental motivation of maintaining concept fidelity. Ablation studies. Effect of the number of concepts and dimensions. We observe that there are no significant differences in performance over a varying number of concepts or dimensions. For all results reported, the number of concepts is set to a number of classes in the dataset, and their dimension is set to 1. For results on varying numbers of concepts and dimensions - refer to Appendix. Effect of the number of concepts and dimensions. 4.5 Concept Fidelity As the RCE framework is explicitly regularized with a concept fidelity regularizer and grounded using prototypes, we would expect high fidelity scores. Table 5 lists the fidelity scores for the aforementioned baselines and our proposed method. Fidelity scores are averaged for each domain when taken as a target (e.g. for the domain (A) in DomainNet, the score is an average of C→A, P→A and R→A). As expected, our method and BotCL, both with specific fidelity regularization outperform all other baseline approaches. Our method outperforms BotCL in most settings, except when the target domains are Art in DomainNet and Clipart in OfficHome due to significant domain dissonance. 4.6 Qualitative Visualization Domain Alignment. We consider the extent to which the models trained using both concept grounding and contrastive learning maintain concept consistency not only within the source domain but also across the target domain as well. To understand what discriminative information is captured by a particular concept, Figure 5 shows the most important prototypes selected from the training set of both the source and target domains corresponding to five randomly selected concepts. We observe that prototypes explaining each concept are visually similar. For more results, refer Appendix. Domain Alignment. Explanation using prototypes. For a given input sample, we also plot the prototypes associated with the highest activated concept, i.e., the important concept. Figure 6 shows the prototypes associated with the concepts most responsible for prediction (highest relevance scores). As can be seen, the prototypes possess distinct features, for eg., they capture the round face of an alarm clock. More results are reported in Appendix. Explanation using prototypes. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

How Reliable Are AI Concepts in Real-World Domain Adaptation Tasks?

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

4 Steps to Achieve Domain-Invariant Concept Learning in AI Systems

Enhancing AI Interpretability: A Guide to Self-Explaining Concept Architectures

Forget Manual Annotation: AI Can Now Learn Concepts on Its Own

4 Steps to Achieve Domain-Invariant Concept Learning in AI Systems

Can AI Concepts Truly Generalize Across Different Domains? Experiments Reveal Answers

4 Steps to Achieve Domain-Invariant Concept Learning in AI Systems

Enhancing AI Interpretability: A Guide to Self-Explaining Concept Architectures

Forget Manual Annotation: AI Can Now Learn Concepts on Its Own

4 Steps to Achieve Domain-Invariant Concept Learning in AI Systems

Can AI Concepts Truly Generalize Across Different Domains? Experiments Reveal Answers

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps