Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 10133 publications
Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models
Yae Jee Cho
Aldi Fahrezi
Gauri Joshi
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024) (2024)
Preview abstract
Foundation models (FMs) adapt well to specific domains or tasks with fine-tuning, and federated learning (FL) enables the potential for privacy-preserving fine-tuning of the FMs with on-device local data. For federated fine-tuning of FMs, we consider the FMs with small to medium parameter sizes of single digit billion at maximum, referred to as on-device FMs (ODFMs) that can be deployed on devices for inference but can only be fine-tuned with parameter efficient methods. In our work, we tackle the data and system heterogeneity problem of federated fine-tuning of ODFMs by proposing a novel method using heterogeneous low-rank approximations (LoRAs), namely HetLoRA. First, we show that the naive approach of using homogeneous LoRA ranks across devices face a trade-off between overfitting and slow convergence, and thus propose HetLoRA, which allows heterogeneous ranks across client devices and efficiently aggregates and distributes these heterogeneous LoRA modules. By applying rank self-pruning locally and sparsity-weighted aggregation at the server, HetLoRA combines the advantages of high and low-rank LoRAs, which achieves improved convergence speed and final performance compared to homogeneous LoRA. Furthermore, HetLoRA offers enhanced computation efficiency compared to full fine-tuning, making it suitable for federated fine-tuning across heterogeneous devices.
View details
A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models
Shengyao Zhuang
Bevan Koopman
Guido Zuccon
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’24) (2024)
Preview abstract
We propose a novel zero-shot document ranking approach based on Large Language Models (LLMs): the Setwise prompting approach. Our approach complements existing prompting approaches for LLM-based zero-shot ranking: Pointwise, Pairwise, and Listwise. Through the first-of-its-kind comparative evaluation within a consistent experimental framework and considering factors like model size, token consumption, latency, among others, we show that existing approaches are inherently characterised by trade-offs between effectiveness and efficiency. We find that while Pointwise approaches score high on efficiency, they suffer from poor effectiveness. Conversely, Pairwise approaches demonstrate superior effectiveness but incur high computational overhead. Our Setwise approach, instead, reduces the number of LLM inferences and the amount of prompt token consumption during the ranking procedure, compared to previous methods. This significantly improves the efficiency of LLM-based zero-shot ranking, while also retaining high zero-shot ranking effectiveness. We make our code and results publicly available at https://github.com/ielab/llm-rankers.
View details
Preview abstract
WindowMirror is a framework for using XR headsets in productivity scenarios. The toolkit provides users with a simulated, extended screen real-estate. It allows users to interact with multiple desktop applications in real-time within a XR environment. Our architecture has two main modules: one a Unity package and a Python backend, which makes it easy to use and extend. WindowMirror supports traditional desktop interaction methods such as mouse, keyboard, and hand tracking. Furthermore, it features a Cylindrical Window Layout, an emerging design pattern which is particularly effective for single-user, egocentric perspectives. The introduction of WindowMirror aims to set a foundation for future research in XR screen-focused productivity scenarios.
View details
The Inside Story of Google’s Quiet Nuclear R&D Quest
IEEE Spectrum (2024)
Preview abstract
Examines how a Google R&D programme sought to accelerate a future of safer, cheaper and more ubiquitous fusion and other nuclear energy. Discusses how the programme was started, its major components: fusion, edge-of-technology, and policy advocacy supporting innovation. Shows successful exits for each part. Beyond telling the sotry, an intents is to show how to move the needle, and get people to think about how they might also help, and show Google has made a difference. Timing of publication marks the 10th anniversary of programme's start.
View details
Preview abstract
Private Everlasting Prediction (PEP), recently introduced by Naor et al. [2023], is a model for differentially private learning in which the learner never publicly releases a hypothesis. Instead, it provides a black-box access to a ``prediction oracle'' that can predict the labels of an endless stream of unlabeled examples drawn from the underlying distribution. Importantly, PEP provides privacy both for the initial training set and for the endless stream of classification queries. We present two conceptual modifications to the definition of PEP, as well as new constructions exhibiting significant improvements over prior work. Specifically, our contributions include:
(1) Robustness: PEP only guarantees accuracy provided that all the classification queries are drawn from the correct underlying distribution. A few out-of-distribution queries might break the validity of the prediction oracle for future queries, even for future queries which are sampled from the correct distribution. We incorporate robustness against such poisoning attacks into the definition of PEP, and show how to obtain it.
(2) Dependence of the privacy parameter delta in the time horizon: We present a relaxed privacy definition, suitable for PEP, that allows us to disconnect the privacy parameter delta from the number of total time steps T. This allows us to obtain algorithms for PEP whose sample complexity is independent from T, thereby making them "truly everlasting". This is in contrast to prior work where the sample complexity grows with polylog(T).
(3) New constructions: Prior constructions for PEP exhibit sample complexity that is quadratic in the VC dimension of the target class. We present new constructions of PEP for axis-aligned rectangles and for decision-stumps, that exhibit sample complexity linear in the dimension (instead of quadratic). We show that our constructions satisfy very strong robustness properties.
View details
Preview abstract
The state-of-the-art for training on-device language models for mobile keyboard applications combines federated learning (FL) with differential privacy (DP) via the DP-Follow-the-Regularized-Leader (DP-FTRL) algorithm. Two variants of DP-FTRL are used in practice, tree aggregation and matrix factorization. However, tree aggregation suffers from significantly suboptimal privacy/utility tradeoffs, while matrix mechanisms require expensive optimization parameterized by hard-to-estimate-in-advance constants, and high runtime memory costs.This paper extends the recently introduced Buffered Linear Toeplitz (BLT) mechanism to multi-participation scenarios. Our BLT-DP-FTRL maintains the ease-of-use advantages of tree aggregation, while essentially matching matrix factorization in terms of utility and privacy. We evaluate BLT-DP-FTRL on the StackOverflow dataset, serving as a re-producible simulation benchmark, and across four on-device language model tasks in a production FL system. Our empirical results highlight the advantages of the BLT mechanism and elevate the practicality and effectiveness of DP in real-world scenarios.
View details
Preview abstract
We present shadow Hamiltonian simulation, a framework for simulating quantum dynamics
using a compressed quantum state that we call the “shadow state”. The amplitudes of this
shadow state are proportional to the expectations of a set of operators of interest. The shadow
state evolves according to its own Schrodinger equation, and under broad conditions can be
simulated on a quantum computer. We analyze a number of applications of this framework to quantum simulation problems. This includes simulating the dynamics of exponentially large systems of free fermions, or exponentially large systems of free bosons, the latter example recovering a recent algorithm for simulating exponentially many classical harmonic oscillators. Shadow Hamiltonian simulation can be extended to simulate expectations of more complex operators such as two-time correlators or Green’s functions, and to study the evolution of operators themselves in the Heisenberg picture
View details
Preview abstract
One of the most basic problems for studying the "price of privacy over time" is the so called private counter problem, introduced by Dwork et al. (2010) and Chan et al. (2011). In this problem, we aim to track the number of events that occur over time, while hiding the existence of every single event. More specifically, in every time step $t\in[T]$ we learn (in an online fashion) that $\Delta_t\geq 0$ new events have occurred, and must respond with an estimate $n_t\approx\sum_{j=1}^t \Delta_j$. The privacy requirement is that all of the outputs together, across all time steps, satisfy event level differential privacy.
The main question here is how our error needs to depend on the total number of time steps $T$ and the total number of events $n$. Dwork et al. (2015) showed an upper bound of $O\left(\log(T)+\log^2(n)\right)$, and Henzinger et al. (2023) showed a lower bound of $\Omega\left(\min\{\log n, \log T\}\right)$. We show a new lower bound of $\Omega\left(\min\{n,\log T\}\right)$, which is tight w.r.t. the dependence on $T$, and is tight in the sparse case where $\log^2 n=O(\log T)$. Our lower bound has the following implications:
* We show that our lower bound extends to the online thresholds problem, where the goal is to privately answer many "quantile queries" when these queries are presented one-by-one. This resolves an open question of Bun et al. (2017).
* Our lower bound implies, for the first time, a separation between the number of mistakes obtainable by a private online learner and a non-private online learner. This partially resolves a COLT'22 open question published by Sanyal and Ramponi.
* Our lower bound also yields the first separation between the standard model of private online learning and a recently proposed relaxed variant of it, called private online prediction.
View details
Preview abstract
This paper presents a Multifunctional wearable
sensing system that integrates flexible Laser-Induced-Graphene
(LIG) based sensors and an Open-Source Analog Front-End
(AFE) chip. The LIG sensors are fabricated on polyimide (PI)
Flexible Printed Circuit Board (FPCB) through CO2 infrared
laser direct-write method. The LIG sensors provide repeatable
high-precision temperature sensing, humidity measurement, and
strain detection capabilities. The temperature sensing charac-
terization shows the resistive LIG sensor has a sensitivity of
-0.0493 %/°C, the linear fit R-square factors ≥ 0.9973 across -40
°C to 125 °C. The capacitive humidity sensor achieves a 23.6
times capacitance at 95% relative humidity (RH) compared to
the value observed in a dry environment. Our proposed AFE
chip contains a hybrid folded-cascode Operational Amplifier
(OPAMP) and a Successive Approximation Register Analog-
to-Digital Converter (SAR ADC). Designed using open-source
analog flow and fabricated in GF180 OpenPDK, the AFE chip
serves as a flexible and universal readout platform, adaptable for
various sensing applications. A real-time demonstration of finger
bending detection is performed to validate the functionality.
The multifunctional sensing capability provide by the wearable
system is attractive for personal healthcare application. This
work underscores the integration of the LIG sensors and the
AFE chip, developed using open-source tools which facilitate
rapid and affordable prototyping for a multifunctional flexible
wearable sensing system.
View details
Connecting Language Technologies with Rich, Diverse Data Sources Covering Thousands of Languages
Sebastian Ruder
Julia Kreutzer
Clara Rivera
Ishank Saxena
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Preview abstract
Contrary to common belief, there are rich and diverse data sources available for many thousands of languages, which can be used to develop technologies for these languages. In this paper, we provide an overview of some of the major online data sources, the types of data that they provide access to, potential applications of this data, and the number of languages that they cover. Even this covers only a small fraction of the data that exists; for example, printed books are published in many languages but few online aggregators exist.
View details
VideoPoet: A Large Language Model for Zero-Shot Video Generation
Dan Kondratyuk
Xiuye Gu
Jonathan Huang
Grant Schindler
Rachel Hornung
Vighnesh Birodkar
Jimmy Yan
Ming-Chang Chiu
Hassan Akbari
Josh Dillon
Agrim Gupta
Meera Hahn
Anja Hauth
David Hendon
Alonso Martinez
Kihyuk Sohn
Xuan Yang
Huisheng Wang
Lu Jiang
ICML (2024)
Preview abstract
We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/
View details
Preview abstract
Advances in deep learning systems have allowed large models to match or surpass human accuracy on a number of skills such as image classification, basic programming, and standardized test taking. As the performance of the most capable models begin to saturate on tasks where humans already achieve high accuracy, it becomes necessary to benchmark models on increasingly complex abilities. One such task is forecasting the future outcome of events. In this work we describe experiments using a novel dataset of real world events and associated human predictions, an evaluation metric to measure forecasting ability, and the accuracy of a number of different LLM based forecasting designs on the provided dataset. Additionally, we analyze the performance of the LLM forecasters against human predictions and find that models still struggle to make accurate predictions about the future. Our follow-up experiments indicate this is likely due to models' tendency to guess that most events are unlikely to occur (which tends to be true for many prediction datasets, but does not reflect actual forecasting abilities). We reflect on next steps for developing a systematic and reliable approach to studying LLM forecasting.
View details
Preview abstract
This is an invited OFC 2024 conference workshop talk regarding a new type of lower-power datacenter optics design choice: linear pluggable optics. In this talk I will discuss the fundamental performance constraints facing linear pluggable optics and their implications on DCN and ML use cases
View details
Preview abstract
Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.
View details
Preview abstract
We propose OmniNOCS, a large-scale monocular dataset with 3D Normalized Object Coordinate Space (NOCS) maps, object masks, and 3D bounding box annotations for indoor and outdoor scenes. OmniNOCS has 20 times more object classes and 200 times more instances than existing NOCS datasets (NOCS-Real275, Wild6D). We use OmniNOCS to train a novel, transformer-based monocular NOCS prediction model (NOCSformer) that can predict accurate NOCS, instance masks and poses from 2D object detections across diverse classes. It is the first NOCS model that can generalize to a broad range of classes when prompted with 2D boxes. We evaluate our model on the task of 3D oriented bounding box prediction, where it achieves comparable results to state-of-the-art 3D detection methods such as Cube R-CNN. Unlike other 3D detection methods, our model also provides detailed and accurate 3D object shape and segmentation. We propose a novel benchmark for the task of NOCS prediction based on OmniNOCS, which we hope will serve as a useful baseline for future work in this area. Our dataset and code is available at the project website: https://omninocs.github.io
View details
