Asma Ghandeharioun
Asma Ghandeharioun, Ph.D., is a senior research scientist with the People + AI Research team at Google DeepMind. She works on aligning AI with human values through better understanding and controlling (language) models, uniquely by demystifying their inner workings and correcting collective misconceptions along the way. While her current research is mostly focused on machine learning interpretability, her previous work spans conversational AI, affective computing, and, more broadly, human-centered AI. She holds a doctorate and master’s degree from MIT and a bachelor’s degree from the Sharif University of Technology. She has been trained as a computer scientist/engineer and has research experience at MIT, Google Research, Microsoft Research, Ecole Polytechnique Fédérale de Lausanne (EPFL), to name a few.
Her work has been published in premier peer-reviewed machine learning venues such as ICLR, NeurIPS, ICML, EMNLP, AAAI, ACII, and AISTATS. She has received awards at NeurIPS and her work has been featured in Wired, Wall Street Journal, and New Scientist.
For more details, visit her personal page.
Her work has been published in premier peer-reviewed machine learning venues such as ICLR, NeurIPS, ICML, EMNLP, AAAI, ACII, and AISTATS. She has received awards at NeurIPS and her work has been featured in Wired, Wall Street Journal, and New Scientist.
For more details, visit her personal page.
Authored Publications
Sort By
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
Chun-Liang Li
Brian Eoff
Rosalind Picard
International Conference on Learning Representations (ICLR) (2022)
Preview abstract
Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued by many scholars. One of the principal benefits of counterfactual explanations is allowing users to explore "what-if" scenarios through what does not and cannot exist in the data, a quality that many other forms of explanation such as heatmaps and influence functions are inherently incapable of doing. However, most previous work on generative explainability cannot disentangle important concepts effectively, produces unrealistic examples, or fails to retain relevant information. We propose a novel approach, DISSECT, that jointly trains a generator, a discriminator, and a concept disentangler to overcome such challenges using little supervision. DISSECT generates Concept Traversals (CTs), defined as a sequence of generated examples with increasing degrees of concepts that influence a classifier's decision. By training a generative model from a classifier's signal, DISSECT offers a way to discover a classifier's inherent "notion" of distinct concepts automatically rather than rely on user-predefined concepts. We show that DISSECT produces CTs that (1) disentangle several concepts, (2) are influential to a classifier's decision and are coupled to its reasoning due to joint training (3), are realistic, (4) preserve relevant information, and (5) are stable across similar inputs. We validate DISSECT on several challenging synthetic and realistic datasets where previous methods fall short of satisfying desirable criteria for interpretability and show that it performs consistently well. Finally, we present experiments showing applications of DISSECT for detecting potential biases of a classifier and identifying spurious artifacts that impact predictions.
View details
Human-centric dialog training via offline reinforcement learning
Judy Hanwen Shen
Craig Ferguson
Agata Lapedriza
Noah Jones
Shixiang Gu
Rosalind Picard
Empirical Methods in Natural Language Processing (EMNLP) (2020)
Preview abstract
How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time, open-ended conversations, which we then use to train and improve the models using offline reinforcement learning (RL). We identify implicit conversational cues including language similarity, elicitation of laughter, sentiment, and more, which indicate positive human feedback, and embed these in multiple reward functions. A well-known challenge is that learning an RL policy in an offline setting usually fails due to the lack of ability to explore and the tendency to make over-optimistic estimates of future reward. These problems become even harder when using RL for language models, which can easily have a 20,000 action vocabulary and many possible reward functions. We solve the challenge by developing a novel class of offline RL algorithms. These algorithms use KL-control to penalize divergence from a pre-trained prior language model, and use a new strategy to make the algorithm pessimistic, instead of optimistic, in the face of uncertainty. We test the resulting dialog model with ratings from 80 users in an open-domain setting and find it achieves significant improvements over existing deep offline RL approaches. The novel offline RL method is viable for improving any existing generative dialog model using a static dataset of human feedback.
View details
Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias
Brian Eoff
Rosalind Picard
ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models (2019)
Preview abstract
Supporting model interpretability for complex phenomena where annotators can legitimately disagree, such as emotion recognition, is a challenging machine learning task. In this work, we show that explicitly quantifying the uncertainty in such settings has interpretability benefits. We use a simple modification of a classical network inference using Monte Carlo dropout to give measures of epistemic and aleatoric uncertainty. We identify a significant correlation between aleatoric uncertainty and human annotator disagreement (r ≈ .3). Additionally, we demonstrate how difficult and subjective training samples can be identified using aleatoric uncertainty and how epistemic uncertainty can reveal data bias that could result in unfair predictions. We identify the total uncertainty as a suitable surrogate for model calibration, i.e. the degree we can trust model's predicted confidence. In addition to explainability benefits, we observe modest performance boosts from incorporating model uncertainty.
View details
