113 citations · 397 across the 33 of their papers we have counts for
34 papers
Quake: Adaptive Indexing for Vector Search
Jason Mohoney, Devesh Sarda, Mengze Tang +5
Vector search, the task of finding the k-nearest neighbors of a query vector against a database of high-dimensional vectors, underpins many machine learning applications, including…
MLKV: Efficiently Scaling up Large Embedding Model Training with Disk-based Key-Value Storage
Yongjun He, Roger Waleffe, Zhichao Han +8
Many modern machine learning (ML) methods rely on embedding models to learn vector representations (embeddings) for a set of entities (embedding tables). As increasingly diverse ML…
Armada: Memory-Efficient Distributed Training of Large-Scale Graph Neural Networks
Roger Waleffe, Devesh Sarda, Jason Mohoney +3
We study distributed training of Graph Neural Networks (GNNs) on billion-scale graphs that are partitioned across machines. Efficient training in this setting relies on min-edge-cu…
Fundamental Challenges in Evaluating Text2SQL Solutions and Detecting Their Limitations
Cedric Renggli, Ihab F. Ilyas, Theodoros Rekatsinas
In this work, we dive into the fundamental challenges of evaluating Text2SQL solutions and highlight potential failure causes and the potential risks of relying on aggregate metric…
Incremental IVF Index Maintenance for Streaming Vector Search
Jason Mohoney, Anil Pacaci, Shihabur Rahman Chowdhury +7
The prevalence of vector similarity search in modern machine learning applications and the continuously changing nature of data processed by these applications necessitate efficien…
TSDS: Data Selection for Task-Specific Model Finetuning
Zifan Liu, Amin Karbasi, Theodoros Rekatsinas
Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of app…
EnergAt: Fine-Grained Energy Attribution for Multi-Tenancy
Hongyu Hè, Michal Friedman, Theodoros Rekatsinas
In the post-Moore's Law era, relying solely on hardware advancements for automatic performance gains is no longer feasible without increased energy consumption, due to the end of D…
Co-design Hardware and Algorithm for Vector Search
Wenqi Jiang, Shigang Li, Yu Zhu +8
Vector search has emerged as the foundation for large-scale information retrieval and machine learning systems, with search engines like Google and Bing processing tens of thousand…
Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
Patrik Okanovic, Roger Waleffe, Vasilis Mageirakos +5
Methods for carefully selecting or generating a small set of training data to learn from, i.e., data pruning, coreset selection, and data distillation, have been shown to be effect…
Growing and Serving Large Open-domain Knowledge Graphs
Ihab F. Ilyas, JP Lacerda, Yunyao Li +5
Applications of large open-domain knowledge graphs (KGs) to real-world problems pose many unique challenges. In this paper, we present extensions to Saga our platform for continuou…
High-Throughput Vector Similarity Search in Knowledge Graphs
Jason Mohoney, Anil Pacaci, Shihabur Rahman Chowdhury +5
There is an increasing adoption of machine learning for encoding data into vectors to serve online recommendation and search use cases. As a result, recent data management systems…
Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale
Ihab F. Ilyas, Theodoros Rekatsinas, Vishnu Konda +3
We introduce Saga, a next-generation knowledge construction and serving platform for powering knowledge-based applications at industrial scale. Saga follows a hybrid batch-incremen…
MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural Networks
Roger Waleffe, Jason Mohoney, Theodoros Rekatsinas +1
We study training of Graph Neural Networks (GNNs) for large-scale graphs. We revisit the premise of using distributed training for billion-scale graphs and show that for graphs tha…
Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
Sahaana Suri, Ihab F. Ilyas, Christopher Ré +1
Structured data, or data that adheres to a pre-defined schema, can suffer from fragmented context: information describing a single entity can be scattered across multiple datasets…
Marius: Learning Massive Graph Embeddings on a Single Machine
Jason Mohoney, Roger Waleffe, Yiheng Xu +2
We propose a new framework for computing the embeddings of large-scale graphs on a single machine. A graph embedding is a fixed length vector representation for each node (and/or e…
Unsupervised Relation Extraction from Language Models using Constrained Cloze Completion
Ankur Goswami, Akshata Bhat, Hadar Ohana +1
We show that state-of-the-art self-supervised language models can be readily used to extract relations from a corpus without the need to train a fine-tuned extractive head. We intr…
Principal Component Networks: Parameter Reduction Early in Training
Roger Waleffe, Theodoros Rekatsinas
Recent works show that overparameterized networks contain small subnetworks that exhibit comparable accuracy to the full model when trained in isolation. These results highlight th…
Record fusion: A learning approach
Alireza Heidari, George Michalopoulos, Shrinu Kushagra +2
Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where…
An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
Deepan Das, Haley Massa, Abhimanyu Kulkarni +1
Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple tran…
Picket: Guarding Against Corrupted Data in Tabular Data during Learning and Inference
Zifan Liu, Zhechun Zhou, Theodoros Rekatsinas
Data corruption is an impediment to modern machine learning deployments. Corrupted data can severely bias the learned model and can also lead to invalid inferences. We present, Pic…
On Robust Mean Estimation under Coordinate-level Corruption
Zifan Liu, Jongho Park, Theodoros Rekatsinas +1
We study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions. We show that this measur…
Fine-Grained Object Detection over Scientific Document Images with Region Embeddings
Ankur Goswami, Joshua McGrath, Shanan Peters +1
We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coar…
Approximate Inference in Structured Instances with Noisy Categorical Observations
Alireza Heidari, Ihab F. Ilyas, Theodoros Rekatsinas
We study the problem of recovering the latent ground truth labeling of a structured instance with categorical random variables in the presence of noisy observations. We present a n…
Learning Functional Dependencies with Sparse Regression
Zhihan Guo, Theodoros Rekatsinas
We study the problem of discovering functional dependencies (FD) from a noisy dataset. We focus on FDs that correspond to statistical dependencies in a dataset and draw connections…