Raha Moraffah

Amrita Bhattacharjee, Tharindu Kumarage, Raha Moraffah et al.

Large language models (LLMs) are increasingly being used for generating text in a variety of use cases, including journalistic news articles. Given the potential malicious nature in which these LLMs can be used to generate disinformation at scale, it is important to build effective detectors for such AI-generated text. Given the surge in development of new LLMs, acquiring labeled training data for supervised detectors is a bottleneck. However, there might be plenty of unlabeled text data available, without information on which generator it came from. In this work we tackle this data problem, in detecting AI-generated news text, and frame the problem as an unsupervised domain adaptation task. Here the domains are the different text generators, i.e. LLMs, and we assume we have access to only the labeled source data and unlabeled target data. We develop a Contrastive Domain Adaptation framework, called ConDA, that blends standard domain adaptation techniques with the representation power of contrastive learning to learn domain invariant representations that are effective for the final unsupervised detection task. Our experiments demonstrate the effectiveness of our framework, resulting in average performance gains of 31.7% from the best performing baselines, and within 0.8% margin of a fully supervised detector. All our code and data is available at https://github.com/AmritaBh/ConDA-gen-text-detection.

Amrita Bhattacharjee, Raha Moraffah, Joshua Garland et al.

With the advent of larger and more complex deep learning models, such as in Natural Language Processing (NLP), model qualities like explainability and interpretability, albeit highly desirable, are becoming harder challenges to tackle and solve. For example, state-of-the-art models in text classification are black-box by design. Although standard explanation methods provide some degree of explainability, these are mostly correlation-based methods and do not provide much insight into the model. The alternative of causal explainability is more desirable to achieve but extremely challenging in NLP due to a variety of reasons. Inspired by recent endeavors to utilize Large Language Models (LLMs) as experts, in this work, we aim to leverage the instruction-following and textual understanding capabilities of recent state-of-the-art LLMs to facilitate causal explainability via counterfactual explanation generation for black-box text classifiers. To do this, we propose a three-step pipeline via which, we use an off-the-shelf LLM to: (1) identify the latent or unobserved features in the input text, (2) identify the input features associated with the latent features, and finally (3) use the identified input features to generate a counterfactual explanation. We experiment with our pipeline on multiple NLP text classification datasets, with several recent LLMs, and present interesting and promising findings.

Paras Sheth, Tharindu Kumarage, Raha Moraffah et al.

Hate speech detection refers to the task of detecting hateful content that aims at denigrating an individual or a group based on their religion, gender, sexual orientation, or other characteristics. Due to the different policies of the platforms, different groups of people express hate in different ways. Furthermore, due to the lack of labeled data in some platforms it becomes challenging to build hate speech detection models. To this end, we revisit if we can learn a generalizable hate speech detection model for the cross platform setting, where we train the model on the data from one (source) platform and generalize the model across multiple (target) platforms. Existing generalization models rely on linguistic cues or auxiliary information, making them biased towards certain tags or certain kinds of words (e.g., abusive words) on the source platform and thus not applicable to the target platforms. Inspired by social and psychological theories, we endeavor to explore if there exist inherent causal cues that can be leveraged to learn generalizable representations for detecting hate speech across these distribution shifts. To this end, we propose a causality-guided framework, PEACE, that identifies and leverages two intrinsic causal cues omnipresent in hateful content: the overall sentiment and the aggression in the text. We conduct extensive experiments across multiple platforms (representing the distribution shift) showing if causal cues can help cross-platform generalization.

Paras Sheth, Raha Moraffah, K. Selçuk Candan et al.

Machine learning models rely on various assumptions to attain high accuracy. One of the preliminary assumptions of these models is the independent and identical distribution, which suggests that the train and test data are sampled from the same distribution. However, this assumption seldom holds in the real world due to distribution shifts. As a result models that rely on this assumption exhibit poor generalization capabilities. Over the recent years, dedicated efforts have been made to improve the generalization capabilities of these models collectively known as -- \textit{domain generalization methods}. The primary idea behind these methods is to identify stable features or mechanisms that remain invariant across the different distributions. Many generalization approaches employ causal theories to describe invariance since causality and invariance are inextricably intertwined. However, current surveys deal with the causality-aware domain generalization methods on a very high-level. Furthermore, we argue that it is possible to categorize the methods based on how causality is leveraged in that method and in which part of the model pipeline is it used. To this end, we categorize the causal domain generalization methods into three categories, namely, (i) Invariance via Causal Data Augmentation methods which are applied during the data pre-processing stage, (ii) Invariance via Causal representation learning methods that are utilized during the representation learning stage, and (iii) Invariance via Transferring Causal mechanisms methods that are applied during the classification stage of the pipeline. Furthermore, this survey includes in-depth insights into benchmark datasets and code repositories for domain generalization methods. We conclude the survey with insights and discussions on future directions.

Tharindu Kumarage, Paras Sheth, Raha Moraffah et al.

In recent years, there has been a rapid proliferation of AI-generated text, primarily driven by the release of powerful pre-trained language models (PLMs). To address the issue of misuse associated with AI-generated text, various high-performing detectors have been developed, including the OpenAI detector and the Stanford DetectGPT. In our study, we ask how reliable these detectors are. We answer the question by designing a novel approach that can prompt any PLM to generate text that evades these high-performing detectors. The proposed approach suggests a universal evasive prompt, a novel type of soft prompt, which guides PLMs in producing "human-like" text that can mislead the detectors. The novel universal evasive prompt is achieved in two steps: First, we create an evasive soft prompt tailored to a specific PLM through prompt tuning; and then, we leverage the transferability of soft prompts to transfer the learned evasive soft prompt from one PLM to another. Employing multiple PLMs in various writing tasks, we conduct extensive experiments to evaluate the efficacy of the evasive soft prompts in their evasion of state-of-the-art detectors.

Paras Sheth, Tharindu Kumarage, Raha Moraffah et al.

Social media platforms, despite their value in promoting open discourse, are often exploited to spread harmful content. Current deep learning and natural language processing models used for detecting this harmful content overly rely on domain-specific terms affecting their capabilities to adapt to generalizable hate speech detection. This is because they tend to focus too narrowly on particular linguistic signals or the use of certain categories of words. Another significant challenge arises when platforms lack high-quality annotated data for training, leading to a need for cross-platform models that can adapt to different distribution shifts. Our research introduces a cross-platform hate speech detection model capable of being trained on one platform's data and generalizing to multiple unseen platforms. To achieve good generalizability across platforms, one way is to disentangle the input representations into invariant and platform-dependent features. We also argue that learning causal relationships, which remain constant across diverse environments, can significantly aid in understanding invariant representations in hate speech. By disentangling input into platform-dependent features (useful for predicting hate targets) and platform-independent features (used to predict the presence of hate), we learn invariant representations resistant to distribution shifts. These features are then used to predict hate speech across unseen platforms. Our extensive experiments across four platforms highlight our model's enhanced efficacy compared to existing state-of-the-art methods in detecting generalized hate speech.

Suraj Jyothi Unni, Raha Moraffah, Huan Liu

Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization datasets for VQA exhibit a unilateral focus on textual shifts while VQA being a multi-modal task contains shifts across both visual and textual domains. We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. Experiments demonstrate VQA-GEN dataset exposes the vulnerability of existing methods to joint multi-modal distribution shifts. validating that comprehensive multi-modal shifts are critical for robust VQA generalization. Models trained on VQA-GEN exhibit improved cross-domain and in-domain performance, confirming the value of VQA-GEN. Further, we analyze the importance of each shift technique of our pipeline contributing to the generalization of the model.

Rajesh Ganguli, Raha Moraffah

Large Language Models (LLMs) have been shown to generate harmful content. However, the underlying causes of such behavior remain under explored. We propose a causal mediation analysis-based approach to identify the causal factors responsible for harmful generation. Our method performs a multi-granular analysis across model layers, modules (MLP and attention blocks), and individual neurons. Extensive experiments on state-of-the-art LLMs indicate that harmful generation arises in the later layers of the model, results primarily from failures in MLP blocks rather than attention blocks, and is associated with neurons that act as a gating mechanism for harmful generation. The results indicate that the early layers in the model are used for a contextual understanding of harmfulness in a prompt, which is then propagated through the model, to generate harmfulness in the late layers, as well as a signal indicating harmfulness through MLP blocks. This is then further propagated to the last layer of the model, specifically to a sparse set of neurons, which receives the signal and determines the generation of harmful content accordingly.

Shu Wan, Saketh Vishnubhatla, Iskander Kushbay et al.

Directed Acyclic Graphs (DAGs) are widely used to represent structured knowledge in scientific and technical domains. However, datasets for real-world DAGs remain scarce because constructing them typically requires expert interpretation of domain documents. We study Doc2SemDAG construction: recovering a preferred semantic DAG from a document together with the cited evidence and context that explain it. This problem is challenging because a document may admit multiple plausible abstractions, the intended structure is often implicit, and the supporting evidence is scattered across prose, equations, captions, and figures. To address these challenges, we leverage scientific papers containing explicit DAG figures as a natural source of supervision. In this setting, the DAG figure provides the DAG structure, while the accompanying text provides context and explanation. We introduce DAGverse, a framework for constructing document-grounded semantic DAGs from online scientific papers. Its core component, DAGverse-Pipeline, is a semi-automatic system designed to produce high-precision semantic DAG examples through figure classification, graph reconstruction, semantic grounding, and validation. As a case study, we test the framework for causal DAGs and release DAGverse-1, a dataset of 108 expert-validated semantic DAGs with graph-level, node-level, and edge-level evidence. Experiments show that DAGverse-Pipeline outperforms existing Vision-Language Models on DAG classification and annotation. DAGverse provides a foundation for document-grounded DAG benchmarks and opens new directions for studying structured reasoning grounded in real-world evidence.

Amrita Bhattacharjee, Raha Moraffah, Joshua Garland et al.

With the development and proliferation of large, complex, black-box models for solving many natural language processing (NLP) tasks, there is also an increasing necessity of methods to stress-test these models and provide some degree of interpretability or explainability. While counterfactual examples are useful in this regard, automated generation of counterfactuals is a data and resource intensive process. such methods depend on models such as pre-trained language models that are then fine-tuned on auxiliary, often task-specific datasets, that may be infeasible to build in practice, especially for new tasks and data domains. Therefore, in this work we explore the possibility of leveraging large language models (LLMs) for zero-shot counterfactual generation in order to stress-test NLP models. We propose a structured pipeline to facilitate this generation, and we hypothesize that the instruction-following and textual understanding capabilities of recent LLMs can be effectively leveraged for generating high quality counterfactuals in a zero-shot manner, without requiring any training or fine-tuning. Through comprehensive experiments on a variety of propreitary and open-source LLMs, along with various downstream tasks in NLP, we explore the efficacy of LLMs as zero-shot counterfactual generators in evaluating and explaining black-box NLP models.

Tharindu Kumarage, Garima Agrawal, Paras Sheth et al.

We have witnessed lately a rapid proliferation of advanced Large Language Models (LLMs) capable of generating high-quality text. While these LLMs have revolutionized text generation across various domains, they also pose significant risks to the information ecosystem, such as the potential for generating convincing propaganda, misinformation, and disinformation at scale. This paper offers a review of AI-generated text forensic systems, an emerging field addressing the challenges of LLM misuses. We present an overview of the existing efforts in AI-generated text forensics by introducing a detailed taxonomy, focusing on three primary pillars: detection, attribution, and characterization. These pillars enable a practical understanding of AI-generated text, from identifying AI-generated content (detection), determining the specific AI model involved (attribution), and grouping the underlying intents of the text (characterization). Furthermore, we explore available resources for AI-generated text forensics research and discuss the evolving challenges and future directions of forensic systems in an AI era.

Zhen Tan, Chengshuai Zhao, Raha Moraffah et al.

Due to their unprecedented ability to process and respond to various types of data, Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial General Intelligence (AGI). As these advanced generative models increasingly form collaborative networks for complex tasks, the integrity and security of these systems are crucial. Our paper, ``The Wolf Within'', explores a novel vulnerability in MLLM societies - the indirect propagation of malicious content. Unlike direct harmful output generation for MLLMs, our research demonstrates how a single MLLM agent can be subtly influenced to generate prompts that, in turn, induce other MLLM agents in the society to output malicious content. Our findings reveal that, an MLLM agent, when manipulated to produce specific prompts or instructions, can effectively ``infect'' other agents within a society of MLLMs. This infection leads to the generation and circulation of harmful outputs, such as dangerous instructions or misinformation, across the society. We also show the transferability of these indirectly generated prompts, highlighting their possibility in propagating malice through inter-agent communication. This research provides a critical insight into a new dimension of threat posed by MLLMs, where a single agent can act as a catalyst for widespread malevolent influence. Our work underscores the urgent need for developing robust mechanisms to detect and mitigate such covert manipulations within MLLM societies, ensuring their safe and ethical utilization in societal applications.

Amrita Bhattacharjee, Raha Moraffah, Joshua Garland et al.

With the advancement in capabilities of Large Language Models (LLMs), one major step in the responsible and safe use of such LLMs is to be able to detect text generated by these models. While supervised AI-generated text detectors perform well on text generated by older LLMs, with the frequent release of new LLMs, building supervised detectors for identifying text from such new models would require new labeled training data, which is infeasible in practice. In this work, we tackle this problem and propose a domain generalization framework for the detection of AI-generated text from unseen target generators. Our proposed framework, EAGLE, leverages the labeled data that is available so far from older language models and learns features invariant across these generators, in order to detect text generated by an unknown target generator. EAGLE learns such domain-invariant features by combining the representational power of self-supervised contrastive learning with domain adversarial training. Through our experiments we demonstrate how EAGLE effectively achieves impressive performance in detecting text generated by unseen target generators, including recent state-of-the-art ones such as GPT-4 and Claude, reaching detection scores of within 4.7% of a fully supervised detector.

Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee et al.

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial perturbations from the attacked inputs, aiming to restore purified samples that retain similarity to the initially attacked ones and are correctly classified by the classifier. Due to the inherent challenges associated with characterizing noise perturbations for discrete inputs, adversarial text purification has been relatively unexplored. In this paper, we investigate the effectiveness of adversarial purification methods in defending text classifiers. We propose a novel adversarial text purification that harnesses the generative capabilities of Large Language Models (LLMs) to purify adversarial text without the need to explicitly characterize the discrete noise perturbations. We utilize prompt engineering to exploit LLMs for recovering the purified examples for given adversarial examples such that they are semantically similar and correctly classified. Our proposed method demonstrates remarkable performance over various classifiers, improving their accuracy under the attack by over 65% on average.

Raha Moraffah, Paras Sheth, Saketh Vishnubhatla et al.

Machine Learning (ML) has become an integral aspect of many real-world applications. As a result, the need for responsible machine learning has emerged, focusing on aligning ML models to ethical and social values, while enhancing their reliability and trustworthiness. Responsible ML involves many issues. This survey addresses four main issues: interpretability, fairness, adversarial robustness, and domain generalization. Feature selection plays a pivotal role in the responsible ML tasks. However, building upon statistical correlations between variables can lead to spurious patterns with biases and compromised performance. This survey focuses on the current study of causal feature selection: what it is and how it can reinforce the four aspects of responsible ML. By identifying features with causal impacts on outcomes and distinguishing causality from correlation, causal feature selection is posited as a unique approach to ensuring ML models to be ethically and socially responsible in high-stakes applications.

Yang Wu, Raha Moraffah, Rujing Yao et al.

Large Language Models (LLMs) have demonstrated an impressive level of general knowledge. However, they often struggle in highly specialized and cost-sensitive domains such as drug discovery and rare disease research due to the lack of expert knowledge. In this paper, we propose a novel framework (PU-ADKA) designed to efficiently enhance domain-specific LLMs by actively engaging domain experts within a fixed budget. Unlike traditional fine-tuning approaches, PU-ADKA selectively identifies and queries the most appropriate expert from a team, taking into account each expert's availability, knowledge boundaries, and consultation costs. We train PU-ADKA using simulations on PubMed data and validate it through both controlled expert interactions and real-world deployment with a drug development team, demonstrating its effectiveness in enhancing LLM performance in specialized domains under strict budget constraints. In addition to outlining our methodological innovations and experimental results, we introduce a new benchmark dataset, CKAD, for cost-effective LLM domain knowledge acquisition to foster further research in this challenging area.

Paras Sheth, Tharindu Kumarage, Raha Moraffah et al.

Content moderation faces a challenging task as social media's ability to spread hate speech contrasts with its role in promoting global connectivity. With rapidly evolving slang and hate speech, the adaptability of conventional deep learning to the fluid landscape of online dialogue remains limited. In response, causality inspired disentanglement has shown promise by segregating platform specific peculiarities from universal hate indicators. However, its dependency on available ground truth target labels for discerning these nuances faces practical hurdles with the incessant evolution of platforms and the mutable nature of hate speech. Using confidence based reweighting and contrastive regularization, this study presents HATE WATCH, a novel framework of weakly supervised causal disentanglement that circumvents the need for explicit target labeling and effectively disentangles input features into invariant representations of hate. Empirical validation across platforms two with target labels and two without positions HATE WATCH as a novel method in cross platform hate speech detection with superior performance. HATE WATCH advances scalable content moderation techniques towards developing safer online communities.

Raha Moraffah, Huan Liu

Sentence-level attacks craft adversarial sentences that are synonymous with correctly-classified sentences but are misclassified by the text classifiers. Under the black-box setting, classifiers are only accessible through their feedback to queried inputs, which is predominately available in the form of class probabilities. Even though utilizing class probabilities results in stronger attacks, due to the challenges of using them for sentence-level attacks, existing attacks use either no feedback or only the class labels. Overcoming the challenges, we develop a novel algorithm that uses class probabilities for black-box sentence-level attacks, investigate the effectiveness of using class probabilities on the attack's success, and examine the question if it is worthy or practical to use class probabilities by black-box sentence-level attacks. We conduct extensive evaluations of our attack comparing with the baselines across various classifiers and benchmark datasets.

Ryan Saklad, Aman Chadha, Oleg Pavlov et al.

Understanding and inferring causal relationships from texts is a core aspect of human cognition and is essential for advancing large language models (LLMs) towards artificial general intelligence. Existing work evaluating LLM causal reasoning primarily focuses on synthetically generated texts which involve straightforward causal relationships that are explicitly mentioned in the text. This fails to reflect the complexities of real-world tasks. In this paper, we investigate whether LLMs are capable of inferring causal relationships from real-world texts. We develop a benchmark drawn from real-world academic literature which includes diverse texts with respect to length, complexity of relationships (different levels of explicitness, number of nodes, and causal relationships), and domains and sub-domains. To the best of our knowledge, our benchmark is the first-ever real-world dataset for this task. Our experiments on this dataset show that LLMs face significant challenges in inferring causal relationships from real-world text, with the best-performing model achieving an average F1 score of only 0.477. Through systematic analysis across aspects of real-world text (degree of confounding, size of graph, length of text, domain), our benchmark offers targeted insights for further research into advancing LLM causal reasoning.

Zhen Tan, Chengshuai Zhao, Raha Moraffah et al.

Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-checking and information searching. In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases by injecting deceptive content into the retrieval database, intentionally changing the model's behavior. This threat is critical as it mirrors real-world usage scenarios where RAG systems interact with publicly accessible knowledge bases, such as web scrapings and user-contributed data pools. To be more realistic, we target a realistic setting where the adversary has no knowledge of users' queries, knowledge base data, and the LLM parameters. We demonstrate that it is possible to exploit the model successfully through crafted content uploads with access to the retriever. Our findings emphasize an urgent need for security measures in the design and deployment of RAG systems to prevent potential manipulation and ensure the integrity of machine-generated content.

Raha Moraffah, Huan Liu

Surrogate-based black-box attacks have exposed the heightened vulnerability of DNNs. These attacks are designed to craft adversarial examples for any samples with black-box target feedback for only a given set of samples. State-of-the-art surrogate-based attacks involve training a discriminative surrogate that mimics the target's outputs. The goal is to learn the decision boundaries of the target. The surrogate is then attacked by white-box attacks to craft adversarial examples similar to the original samples but belong to other classes. With limited samples, the discriminative surrogate fails to accurately learn the target's decision boundaries, and these surrogate-based attacks suffer from low success rates. Different from the discriminative approach, we propose a generative surrogate that learns the distribution of samples residing on or close to the target's decision boundaries. The distribution learned by the generative surrogate can be used to craft adversarial examples that have imperceptible differences from the original samples but belong to other classes. The proposed generative approach results in attacks with remarkably high attack success rates on various targets and datasets.

Lu Cheng, Ruocheng Guo, Raha Moraffah et al.

The convenient access to copious multi-faceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-based learning, i.e., causal machine learning (causal learning). Recent years have therefore witnessed great effort in developing causal learning algorithms aiming to help AI achieve human-level intelligence. Due to the lack-of ground-truth data, one of the biggest challenges in current causal learning research is algorithm evaluations. This largely impedes the cross-pollination of AI and causal inference, and hinders the two fields to benefit from the advances of the other. To bridge from conventional causal inference (i.e., based on statistical methods) to causal learning with big data (i.e., the intersection of causal inference and machine learning), in this survey, we review commonly-used datasets, evaluation methods, and measures for causal learning using an evaluation pipeline similar to conventional machine learning. We focus on the two fundamental causal-inference tasks and causality-aware machine learning tasks. Limitations of current evaluation procedures are also discussed. We then examine popular causal inference tools/packages and conclude with primary challenges and opportunities for benchmarking causal learning algorithms in the era of big data. The survey seeks to bring to the forefront the urgency of developing publicly available benchmarks and consensus-building standards for causal learning evaluation with observational data. In doing so, we hope to broaden the discussions and facilitate collaboration to advance the innovation and application of causal learning.

Raha Moraffah, Paras Sheth, Mansooreh Karami et al.

Time series data is a collection of chronological observations which is generated by several domains such as medical and financial fields. Over the years, different tasks such as classification, forecasting, and clustering have been proposed to analyze this type of data. Time series data has been also used to study the effect of interventions over time. Moreover, in many fields of science, learning the causal structure of dynamic systems and time series data is considered an interesting task which plays an important role in scientific discoveries. Estimating the effect of an intervention and identifying the causal relations from the data can be performed via causal inference. Existing surveys on time series discuss traditional tasks such as classification and forecasting or explain the details of the approaches proposed to solve a specific task. In this paper, we focus on two causal inference tasks, i.e., treatment effect estimation and causal discovery for time series data, and provide a comprehensive review of the approaches in each task. Furthermore, we curate a list of commonly used evaluation metrics and datasets for each task and provide in-depth insight. These metrics and datasets can serve as benchmarks for research in the field.

Bahman Moraffah, Christ Richmond, Raha Moraffah et al.

Robust tracking of a target in a clutter environment is an important and challenging task. In recent years, the nearest neighbor methods and probabilistic data association filters were proposed. However, the performance of these methods diminishes as the number of measurements increases. In this paper, we propose a robust generative approach to effectively model multiple sensor measurements for tracking a moving target in an environment with high clutter. We assume a time-dependent number of measurements that include sensor observations with unknown origin, some of which may only contain clutter with no additional information. We robustly and accurately estimate the trajectory of the moving target in a high clutter environment with an unknown number of clutters by employing Bayesian nonparametric modeling. In particular, we employ a class of joint Bayesian nonparametric models to construct the joint prior distribution of target and clutter measurements such that the conditional distributions follow a Dirichlet process. The marginalized Dirichlet process prior of the target measurements is then used in a Bayesian tracker to estimate the dynamically-varying target state. We show through experiments that the tracking performance and effectiveness of our proposed framework are increased by suppressing high clutter measurements. In addition, we show that our proposed method outperforms existing methods such as nearest neighbor and probability data association filters.

Raha Moraffah, Bahman Moraffah, Mansooreh Karami et al.

We propose a generative Causal Adversarial Network (CAN) for learning and sampling from conditional and interventional distributions. In contrast to the existing CausalGAN which requires the causal graph to be given, our proposed framework learns the causal relations from the data and generates samples accordingly. The proposed CAN comprises a two-fold process namely Label Generation Network (LGN) and Conditional Image Generation Network (CIGN). The LGN is a GAN-based architecture which learns and samples from the causal model over labels. The sampled labels are then fed to CIGN, a conditional GAN architecture, which learns the relationships amongst labels and pixels and pixels themselves and generates samples based on them. This framework is equipped with an intervention mechanism which enables. the model to generate samples from interventional distributions. We quantitatively and qualitatively assess the performance of CAN and empirically show that our model is able to generate both interventional and conditional samples without having access to the causal graph for the application of face generation on CelebA data.

Raha Moraffah, Mansooreh Karami, Ruocheng Guo et al.

Machine learning models have had discernible achievements in a myriad of applications. However, most of these models are black-boxes, and it is obscure how the decisions are made by them. This makes the models unreliable and untrustworthy. To provide insights into the decision making processes of these models, a variety of traditional interpretable models have been proposed. Moreover, to generate more human-friendly explanations, recent work on interpretability tries to answer questions related to causality such as "Why does this model makes such decisions?" or "Was it a specific feature that caused the decision made by the model?". In this work, models that aim to answer causal questions are referred to as causal interpretable models. The existing surveys have covered concepts and methodologies of traditional interpretability. In this work, we present a comprehensive survey on causal interpretable models from the aspects of the problems and methods. In addition, this survey provides in-depth insights into the existing evaluation metrics for measuring interpretability, which can help practitioners understand for what scenarios each evaluation metric is suitable.

Raha Moraffah, Kai Shu, Adrienne Raglin et al.

Studies show that the representations learned by deep neural networks can be transferred to similar prediction tasks in other domains for which we do not have enough labeled data. However, as we transition to higher layers in the model, the representations become more task-specific and less generalizable. Recent research on deep domain adaptation proposed to mitigate this problem by forcing the deep model to learn more transferable feature representations across domains. This is achieved by incorporating domain adaptation methods into deep learning pipeline. The majority of existing models learn the transferable feature representations which are highly correlated with the outcome. However, correlations are not always transferable. In this paper, we propose a novel deep causal representation learning framework for unsupervised domain adaptation, in which we propose to learn domain-invariant causal representations of the input from the source domain. We simulate a virtual target domain using reweighted samples from the source domain and estimate the causal effect of features on the outcomes. The extensive comparative study demonstrates the strengths of the proposed model for unsupervised domain adaptation via causal representations.

Vineeth Rakesh, Ruocheng Guo, Raha Moraffah et al.

Modeling spillover effects from observational data is an important problem in economics, business, and other fields of research. % It helps us infer the causality between two seemingly unrelated set of events. For example, if consumer spending in the United States declines, it has spillover effects on economies that depend on the U.S. as their largest export market. In this paper, we aim to infer the causation that results in spillover effects between pairs of entities (or units), we call this effect as \textit{paired spillover}. To achieve this, we leverage the recent developments in variational inference and deep learning techniques to propose a generative model called Linked Causal Variational Autoencoder (LCVA). Similar to variational autoencoders (VAE), LCVA incorporates an encoder neural network to learn the latent attributes and a decoder network to reconstruct the inputs. However, unlike VAE, LCVA treats the \textit{latent attributes as confounders that are assumed to affect both the treatment and the outcome of units}. Specifically, given a pair of units $u$ and $\bar{u}$, their individual treatment and outcomes, the encoder network of LCVA samples the confounders by conditioning on the observed covariates of $u$, the treatments of both $u$ and $\bar{u}$ and the outcome of $u$. Once inferred, the latent attributes (or confounders) of $u$ captures the spillover effect of $\bar{u}$ on $u$. Using a network of users from job training dataset (LaLonde (1986)) and co-purchase dataset from Amazon e-commerce domain, we show that LCVA is significantly more robust than existing methods in capturing spillover effects.