Maryam Karimzadehgan
As the Engineering Lead for Android Intelligence, Dr. Maryam Karimzadehgan is at the forefront of developing cutting-edge Generative AI models. Her impressive record includes over 35 research papers, 10 patents, and prestigious awards like the Google PhD Fellowship and the Yahoo! Key Scientific Challenges Award. She earned her PhD from the University of Illinois at Urbana-Champaign.
Authored Publications
Sort By
Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation
Li Ding
NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World (2023)
Preview abstract
We introduce EV3, a novel meta-optimization framework designed to efficiently train scalable machine learning models through an intuitive explore-assess-adapt protocol. In each iteration of EV3, we explore various model parameter updates, assess them using pertinent evaluation methods, and then adapt the model based on the optimal updates and previous progress history. EV3 offers substantial flexibility without imposing stringent constraints like differentiability on the key objectives relevant to the tasks of interest, allowing for exploratory updates with intentionally-biased gradients and through a diversity of losses and optimizers.
Additionally, the assessment phase provides reliable safety controls to ensure robust generalization, and can dynamically prioritize tasks in scenarios with multiple objectives. With inspiration drawn from evolutionary algorithms, meta-learning, and neural architecture search, we investigate an application of EV3 to knowledge distillation. Our experimental results illustrate EV3’s capability to safely explore the modeling landscape, while hinting at its potential applicability across numerous domains due to its inherent flexibility and adaptability. Finally, we provide a JAX implementation of EV3, along with source code for experiments, available
at: https://github.com/google-research/google-research/tree/master/ev3.
View details
Overcoming Prior Misspecification in Online Learning to Rank
Mohammadjavad Azizi
International Conference on Artificial Intelligence and Statistics, PMLR (2023), pp. 594-614
Preview abstract
The recent literature on online learning to rank (LTR) has established the utility of prior knowledge to Bayesian ranking bandit algorithms. However, a major limitation of existing work is the requirement for the prior used by the algorithm to match the true prior. In this paper, we propose and analyze adaptive algorithms that address this issue and additionally extend these results to the linear and generalized linear models. We also consider scalar relevance feedback on top of click feedback. Moreover, we demonstrate the efficacy of our algorithms using both synthetic and real-world experiments.
View details
IMO^3: Interactive Multi-Objective Off-Policy Optimization
Nan Wang
Hongning Wang
Branislav Kveton
Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-22), Vienna (2022), pp. 3523-3529
Preview abstract
Most real-world optimization problems have multiple objectives. A system designer needs to find a policy that trades off these objectives to reach a desired operating point. This problem has been studied extensively in the setting of known objective functions. However, we consider a more practical but challenging setting of unknown objective functions. In industry, optimization under this setting is mostly approached with online A/B testing, which is often costly and inefficient. As an alternative, we propose Interactive Multi-Objective Off-policy Optimization (IMO3). The key idea of IMO3 is to interact with a system designer using policies evaluated in an off-policy fashion to uncover which policy maximizes her unknown utility function. We theoretically show that IMO3 identifies a near-optimal policy with high probability, depending on the amount of designer feedback and training data for off-policy estimation. We demonstrate its effectiveness empirically on several multi-objective optimization problems.
View details
Preview abstract
We propose a bandit algorithm that explores purely by randomizing its past observations. In particular, the sufficient optimism in the mean reward estimates is achieved by exploiting the variance in the past observed rewards. We name the algorithm \textbf{C}apitalizing \textbf{O}n \textbf{Re}wards (\core). The algorithm is general and can be easily applied to different bandit settings. The main benefit of \core is that its exploration is fully data-dependent. It does not rely on any external noise and adapts to different problems without parameter tuning. We derive a $\tilde O(d\sqrt{n\log K})$ gap-free bound on the $n$-round regret of \core in a stochastic linear bandit, where $d$ is the number of features and $K$ is the number of arms. Extensive empirical evaluation on multiple synthetic and real-world problems demonstrates the effectiveness of \core.
View details
Separate And Attend in Personal Email Search
Yu Meng
Proceedings of the 13th ACM International Conference on Web Search and Data Mining (WSDM) (2020)
Preview abstract
In personal email search, user queries often impose different requirements on different aspects of the retrieved emails. For example, the query "my recent flight to the US'" requires emails to be ranked based on both textual contents and recency of the email documents, while other queries such as "medical history'" do not impose any constraints on the recency of the email. Recent deep learning-to-rank models for personal email search often directly concatenate dense numerical features with embedded sparse features (e.g, n-gram embeddings). In this paper, we first show with a set of experiments on synthetic datasets that direct concatenation of dense and sparse features does not lead to the optimal search performance of deep neural ranking models.
To effectively incorporate both sparse and dense email features into personal email search ranking, we propose a novel neural model, sepattn. sepattn first builds two separate neural models to learn from sparse and dense features respectively, and then applies an attention mechanism at the prediction level to derive the final prediction from these two models.
We conduct a comprehensive set of experiments on a large-scale email search dataset, and demonstrate that our sepattn model consistently improves the search quality over the baseline models.
View details
Domain Adaptation for Enterprise Email Search
Brandon Tran
Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (2019)
Preview abstract
In the enterprise email search setting, the same search engine often powers multiple enterprises from various industries: technology, education, manufacturing, etc. However, using the same global ranking model across different enterprises may result in suboptimal search quality, due to the corpora differences and distinct information needs. On the other hand, training an individual ranking model for each enterprise may be infeasible, especially for smaller institutions with limited data. To address this data challenge, in this paper we propose a domain adaptation approach that fine-tunes the global model to each individual enterprise. In particular, we propose a novel application of the Maximum Mean Discrepancy (MMD) approach to information retrieval, which attempts to bridge the gap between the global data distribution and the distribution arising from an individual enterprise. We conduct a comprehensive set of experiments on a large-scale email search engine, and demonstrate that the MMD approach consistently improves the search quality for multiple individual domains, both in comparison to the global ranking model, as well as several competitive domain adaptation baselines including adversarial learning methods.
View details
Multi-Task Learning for Personal Search Ranking with Query Clustering
Jiaming Shen
Proceedings of ACM Conference on Information and Knowledge Management (CIKM) (2018)
Preview abstract
User needs vary significantly across different tasks, and therefore
their queries will also vary significantly in their expressiveness
and semantics. Many studies have been proposed
to model such query diversity by obtaining query types and
building query-dependent ranking models. To obtain query
types, these studies typically require either a labeled query
dataset or clicks from multiple users aggregated over the
same document. These techniques, however, are not applicable
when manual query labeling is not viable, and aggregated
clicks are unavailable due to the private nature of the document
collection, e.g., in personal search scenarios. Therefore,
in this paper, we study the problem of how to obtain query
type in an unsupervised fashion and how to leverage this information
using query-dependent ranking models in personal
search. We first develop a hierarchical clustering algorithm
based on truncated SVD and varimax rotation to obtain
coarse-to-fine query types. Then, we propose three query-dependent
ranking models, including two neural models that
leverage query type information as additional features, and
one novel multi-task neural model that is trained to simultaneously
rank documents and predict query types. We evaluate
our ranking models using the click data collected from one of
the world’s largest personal search engines. The experiments
demonstrate that the proposed multi-task model can significantly
outperform the baseline neural models, which either
do not incorporate query type information or just simply
feed query type as an additional feature. To the best of our
knowledge, this is the first successful application of query-dependent
multi-task learning in personal search ranking.
View details