Rama Kumar Pasumarthi
Authored Publications
Sort By
RD-Suite: A Benchmark for Ranking Distillation
He Zhang
37th Conference on Neural Information Processing Systems (NeurIPS) (2023)
Preview abstract
The distillation of ranking models has become an important topic in both academia and industry. In recent years, several advanced methods have been proposed to tackle this problem, often leveraging ranking information from teacher rankers that is absent in traditional classification settings. To date, there is no well-established consensus on how to evaluate this class of models. Moreover, inconsistent benchmarking on a wide range of tasks and datasets make it difficult to assess or invigorate advances in this field. This paper first examines representative prior arts on ranking distillation, and raises three questions to be answered around methodology and reproducibility. To that end, we propose a systematic and unified benchmark, Ranking Distillation Suite (RD-Suite), which is a suite of tasks with 4 large realworld datasets, encompassing two major modalities (textual and numeric) and two applications (standard distillation and distillation transfer). RD-Suite consists of benchmark results that challenge some of the common wisdom in the field, and the release of datasets with teacher scores and evaluation scripts for future research. RD-Suite paves the way towards better understanding of ranking distillation, facilities more research in this direction, and presents new challenges.
View details
Preview abstract
Existing work on search result diversification typically falls into the "next document" paradigm, that is, selecting the next document based on the ones already chosen. A sequential process of selecting documents one-by-one is naturally modeled in learning-based approaches. However, such a process makes the learning difficult because there are an exponential number of ranking lists to consider. Sampling is usually used to reduce the computational complexity but this makes the learning less effective. In this paper, we propose a soft version of the "next document" paradigm in which we associate each document with an approximate rank, and thus the subtopics covered prior to a document can also be estimated. We show that we can derive differentiable diversification-aware losses, which are smooth approximation of diversity metrics like alpha-NDCG, based on these estimates. We further propose to optimize the losses in the learning-to-rank setting using neural distributed representations of queries and documents. Experiments are conducted on the public benchmark TREC datasets. By comparing with an extensive list of baseline methods, we show that our Diversification-Aware LEarning-TO-Rank (DALETOR) approaches outperform them by a large margin, while being much simpler during learning and inference.
View details
Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees?
Yi Tay
International Conference on Learning Representations (ICLR) (2021)
Preview abstract
Despite the success of neural models in many major machine learning problems and recently published neural learning to rank (LTR) papers in top venues, the effectiveness of neural models on traditional LTR problems is still not widely acknowledged. We first validate the concern by showing that most recent neural LTR models are, by a large margin, inferior to the best publicly available tree-based implementation, which is sometimes ignored in recent neural LTR papers. We then investigate why existing neural LTR suffers by identifying several of its weaknesses. To that end, we propose a new neural LTR framework that mitigates these weaknesses, by borrowing ideas from several research fields. Our models are able to perform comparatively with the strong tree-based baseline, while outperforming recently published neural learning to rank methods by a large margin. Our results also serve as a benchmark for neural learning to rank models.
View details
Improving Cloud Storage Search with User Activity
Proceedings of the 14th International Conference on Web Search and Data Mining (WSDM '21), ACM (2021)
Preview abstract
Cloud-based file storage platforms such as Google Drive are widely used as a means for storing, editing and sharing personal and organizational documents. In this paper, we improve search ranking quality for cloud storage platforms by utilizing user activity logs. Different from search logs, activity logs capture general document usage activity beyond search, such as opening, editing and sharing documents. We propose to automatically learn text embeddings that are effective for search ranking from activity logs. We develop a novel co-access signal, i.e., whether two documents were accessed by a user around the same time, to train deep semantic matching models that are useful for improving the search ranking quality. We confirm that activity-trained semantic matching models can improve ranking by conducting extensive offline experimentation using Google Drive search and activity logs. To the best of our knowledge, this is the first work to examine the benefits of leveraging document usage activity at large scale for cloud storage search; as such it can shed light on using such activity in scenarios where direct collection of search-specific interactions (e.g., query and click logs) may be expensive or infeasible.
View details
RankDistil: Distillation for Ranking
Aditya Krishna Menon
AISTATS 2021 (2021)
Preview abstract
Knowledge distillation is an approach to improve the performance of a student model by using the knowledge of a complex teacher. Despite its success in several deep learning applications, the study of distillation is mostly confined to classification settings. In particular, the use of distillation in top-k ranking settings, where the goal is to rank k most relevant items correctly, remains largely unexplored. In this paper, we study such ranking problems through the lens of distillation. We present a framework for distillation for top-k ranking and establish connections with the existing ranking methods. The core idea of this framework is to preserve the ranking at the top by matching the k largest scores of student and teacher while penalizing large scores for items ranked low by the teacher. Building on our framework, we develop a novel distillation approach, RankDistil, specifically catered towards ranking problems with a large number of items to rank. Finally, we conduct experiments which demonstrate that RankDistil yields benefits over commonly used baselines for ranking problems.
View details
Permutation Equivariant Document Interaction Network for Neural Learning to Rank
Proceedings of the 2020 ACM SIGIR International Conference on the Theory of Information Retrieval (ICTIR 2020)
Preview abstract
How to leverage cross-document interactions to improve ranking performance is an important topic in information retrieval research. The recent developments in deep learning show strength in modeling complex relationships across sequences and sets. It thus motivates us to study how to leverage cross-document interactions for learning-to-rank in the deep learning framework. In this paper, we formally define the permutation equivariance requirement for a scoring function that captures cross-document interactions. We then propose a self-attention based document interaction network that extends any univariate scoring function with contextual features capturing cross-document interactions. We show that it satisfies the permutation equivariance requirement, and can generate scores for document sets of varying sizes.
Our proposed methods can automatically learn to capture document interactions without any auxiliary information, and can scale across large document sets. We conduct experiments on four ranking datasets: the public benchmarks WEB30K and Istella, as well as Gmail search and Google Drive Quick Access datasets. Experimental results show that our proposed methods lead to significant quality improvements over state-of-the-art neural ranking models, and are competitive with state-of-the-art gradient boosted decision tree (GBDT) based models on the WEB30K dataset.
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
TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
Sebastian Bruch
Jan Pfeifer
Rohan Anil
Stephan Wolf
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (2019), pp. 2970-2978
Preview abstract
Learning-to-Rank deals with maximizing the utility of a list of examples presented to the user, with items of higher relevance being prioritized. It has several practical applications such as large-scale search, recommender systems, document summarization and question answering. While there is widespread support for classification and regression based learning, support for learning-to-rank in deep learning has been limited.
We propose TensorFlow Ranking, the first open source library for solving large-scale ranking problems in a deep learning framework. It is highly configurable and provides easy-to-use APIs to support different scoring mechanisms, loss functions and evaluation metrics in the learning-to-rank setting. Our library is developed on top of TensorFlow and can thus fully leverage the advantages of this platform. For example, it is highly scalable, both in training and in inference, and can be used to learn ranking models over massive amounts of user activity data, which can include heterogeneous dense and sparse features. We empirically demonstrate the effectiveness of our library in learning ranking functions for large-scale search and recommendation applications in Gmail and Google Drive. We also show that ranking models built using our model scale well for distributed training, without significant impact in metrics. The proposed library is available to the open source community, with the hope that it facilitates further academic research and industrial applications in the field of learning-to-rank.
View details
TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
Sebastian Nima Bruch
Jan Pfeifer
Rohan Anil
Stephan Wolf
arXiv preprint (2018)
Preview abstract
TensorFlow Ranking is the first open source library for solving large-scale ranking problems in a deep learning framework. It is highly configurable and provides easy-to-use APIs to support different scoring mechanisms, loss functions and evaluation metrics in the learning-to-rank setting. Our library is developed on top of TensorFlow and can thus fully leverage the advantages of this platform. For example, it is highly scalable, both in training and in inference, and can be used to learn ranking models over massive amounts of user activity data. We empirically demonstrate the effectiveness of our library in learning ranking functions for large-scale search and recommendation applications in Gmail and Google Drive.
View details
