Classification algorithms

Context, language modeling, and multimodal data in finance

Sanjiv Das, Connor Giggins, John He, George Karypis, Sandeep Krishnamurthy, Mitali Mahajan, Nagpurnanand Prabhala, Dylan Slack, Rob van Dusen, Shenghua Yue, Sheng Zha, Shuai Zheng

The Journal of Financial Data Science Summer

2021

The authors enhance pretrained language models with Securities and Exchange Commission filings data to create better language representations for features used in a predictive model. Specifically, they train RoBERTa class models with additional financial regulatory text, which they denote as a class of RoBERTa-Fin models. Using different datasets, the authors assess whether there is material improvement

Conversational AI

Multi-task pre-finetuning for zero-shot cross lingual transfer

Moukthika Yerramilli, Pritam Varma, Anurag Dwarakanath

ICON 2021

2021

Building machine learning models for low resource languages is extremely challenging due to the lack of available training data (either un-annotated or annotated). To support such scenarios, zero-shot cross lingual transfer is used where the machine learning model is trained on a resource rich language and is directly tested on the resource poor language. In this paper, we present a technique which improves

Conversational AI

Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features

Jiuhai Chen, Jonas Mueller, Vassilis N. Ioannidis, Soji Adeshina, Yangkun Wang, Tom Goldstein, David Wipf

NeurIPS 2021

2021

For supervised learning with tabular data, decision tree ensembles produced via boosting techniques generally dominate real-world applications involving iid training/test sets. However for graph data where the iid assumption is violated due to structured relations between samples, it remains unclear how to best incorporate this structure within existing boosting pipelines. To this end, we propose a generalized

Machine learning

Finding needles in heterogeneous haystacks

Bijaya Adhikari, Liangyue Li, Nikhil Rao, Karthik Subbian

IAAI 2022

2021

Due to intense competition and lack of real estate on the front page of large e-commerce platforms, sellers are sometimes motivated to garner non-genuine signals (clicks, add-to-carts, purchases) on their products, to make them appear more appealing to customers. This hurts customers’ trust on the platform, and also hurts genuine sellers who sell their items without looking to game the system. While it

Machine learning

NimbleLearn: A scalable and fast batch-mode active learning approach

Ruoyan Kong, Zhanlong Qiu, Yang Liu, Qi Zhao

ICDM 2021

2021

Batch-mode active learning iteratively selects a batch of unlabeled samples for labelling to maximize model performance and reduce total runtime. To select the most informative and diverse batch, existing methods usually calculate the correlation between samples within a batch, leading to combinatorial optimization problems which are inefficient, complex, and limited to linear models for approximated solutions

Machine learning

Minimax group fairness: Algorithms and experiments

Emily Diana, Wesley Gill, Michael Kearns, Krishnaram Kenthapadi, Aaron Roth

AIES 2021

2021

We consider a recently introduced framework in which fairness is measured by worst-case outcomes across groups, rather than by the more standard differences between group outcomes. In this framework we provide provably convergent oracle-efficient learning algorithms (or equivalently, reductions to non-fair learning) for minimax group fairness. Here the goal is that of minimizing the maximum error across

Machine learning

Towards unbiased and accurate deferral to multiple experts

Vijay Keswani, Matthew Lease, Krishnaram Kenthapadi

AIES 2021

2021

Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidence in its inference. Our goal is to design mechanisms for ensuring accuracy and fairness in such prediction systems that combine machine learning model inferences and domain expert predictions. Prior work on “deferral systems”

Machine learning

Mixed-privacy forgetting in deep networks

Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, Stefano Soatto

CVPR 2021

2021

We show that the influence of a subset of the training samples can be removed – or “forgotten” – from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of remaining information after forgetting. Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting, where

Security, privacy, and abuse prevention

LQF: Linear quadratic fine-tuning

Alessandro Achille, Aditya Golatkar, Avinash Ravichandran, Marzia Polito, Stefano Soatto

CVPR 2021

2021

Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization. Such desirable properties are absent in deep neural networks (DNNs), typically trained by non-linear fine-tuning of a pre-trained model. Previous attempts to linearize DNNs have led to interesting

Computer vision

Compatibility-aware heterogeneous visual search

Rahul Duggal, Hao Zhou, Shuo Yang, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto

CVPR 2021

2021

We tackle the problem of visual search under resource constraints. Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images. Such systems inherently face a hard accuracy-efficiency trade-off: the embedding model needs to be large enough to ensure high accuracy, yet small enough to enable query-embedding computation on resource-constrained platforms

Computer vision

Classification algorithms

Work with us