Leo Feng

Tree Cross Attention

Frederick Tung

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for e… (see more)ach prediction, Cross Attention scans the full set of

2024-01-16

ICLR.cc/2024/Conference (poster)

Tree Cross Attention

Frederick Tung

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

2023-09-29

ArXiv (preprint)

arxiv.org

Tree Cross Attention

Frederick Tung

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

2023-09-29

ArXiv (preprint)

arxiv.org

Constant Memory Attention Block

Frederick Tung

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

2023-06-20

ICML.cc/2023/Workshop/ES-FoMO (poster)

Latent Bottlenecked Attentive Neural Processes

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on… (see more) a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong performance but require quadratic computation with respect to the number of context datapoints, significantly limiting its scalability. Conversely, existing sub-quadratic NP variants perform significantly worse than that of TNPs. Tackling this issue, we propose Latent Bottlenecked Attentive Neural Processes (LBANPs), a new computationally efficient sub-quadratic NP variant, that has a querying computational complexity independent of the number of context datapoints. The model encodes the context dataset into a constant number of latent vectors on which self-attention is performed. When making predictions, the model retrieves higher-order information from the context dataset via multiple cross-attention mechanisms on the latent vectors. We empirically show that LBANPs achieve results competitive with the state-of-the-art on meta-regression, image completion, and contextual multi-armed bandits. We demonstrate that LBANPs can trade-off the computational cost and performance according to the number of latent vectors. Finally, we show LBANPs can scale beyond existing attention-based NP variants to larger dataset settings.

2023-02-01

ICLR.cc/2023/Conference (poster)

Constant Memory Attentive Neural Processes

Frederick Tung

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

2023-01-01

arXiv.org (preprint)

Efficient Queries Transformer Neural Processes

Hossein Hajimirsadeghi

Mohamed Osama Ahmed

2022-10-21

NeurIPS.cc/2022/Workshop/MetaLearn (poster)

Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization

The ability to accelerate the design of biological sequences can have a substantial impact on the progress of the medical field. The problem… (see more) can be framed as a global optimization problem where the objective is an expensive black-box function such that we can query large batches restricted with a limitation of a low number of rounds. Bayesian Optimization is a principled method for tackling this problem. However, the astronomically large state space of biological sequences renders brute-force iterating over all possible sequences infeasible. In this paper, we propose MetaRLBO where we train an autoregressive generative model via Meta-Reinforcement Learning to propose promising sequences for selection via Bayesian Optimization. We pose this problem as that of finding an optimal policy over a distribution of MDPs induced by sampling subsets of the data acquired in the previous rounds. Our in-silico experiments show that meta-learning over such ensembles provides robustness against reward misspecification and achieves competitive results compared to existing strong baselines.

2022-09-13

ArXiv (preprint)

arxiv.org

Continuous-Time Meta-Learning with Forward Mode Differentiation

Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learni… (see more)ng (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specifically, representations of the inputs are meta-learned such that a task-specific linear classifier is obtained as a solution of an ordinary differential equation (ODE). Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous, as opposed to a fixed and discrete number of gradient steps. As a consequence, we can optimize the amount of adaptation necessary to solve a new task using stochastic gradient descent, in addition to learning the initial conditions as is standard practice in gradient-based meta-learning. Importantly, in order to compute the exact meta-gradients required for the outer-loop updates, we devise an efficient algorithm based on forward mode differentiation, whose memory requirements do not scale with the length of the learning trajectory, thus allowing longer adaptation in constant memory. We provide analytical guarantees for the stability of COMLN, we show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.

2022-01-28

ICLR.cc/2022/Conference (spotlight)