Publications

Joint Multimodal Transformer for Emotion Recognition in the Wild

Paul Waligora

Muhammad Haseeb Aslam

Muhammad Osama Zeeshan

Soufiane Belharbi

Alessandro Lameiras Koerich

Marco Pedersoli

Simon Bacon

Éric Granger

Multimodal emotion recognition (MMER) systems typically outperform unimodal systems by leveraging the inter-and intra-modal relationships be… (see more)tween, e.g., visual, textual, physiological, and auditory modalities. This paper proposes an MMER method that relies on a joint multi-modal transformer (JMT) for fusion with key-based cross-attention. This framework can exploit the complementary nature of diverse modalities to improve predictive accuracy. Separate backbones capture intra-modal spatiotemporal dependencies within each modality over video sequences. Subsequently, our JMT fusion architecture integrates the individual modality embeddings, allowing the model to effectively capture inter- and intra-modal relationships. Extensive experiments on two challenging expression recognition tasks – (1) dimensional emotion recognition on the Affwild2 dataset (with face and voice) and (2) pain estimation on the Biovid dataset (with face and biosensors) – indicate that our JMT fusion can provide a cost-effective solution for MMER. Empirical results show that MMER systems with our proposed fusion allow us to outperform relevant baseline and state-of-the-art methods. Code is available at: https://github.com/PoloWlg/Joint-Multimodal-Transformer-6th-ABAW

2024-06-16

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (published)

doi.org

arxiv.org

Learning Generative Population Models From Multiple Clinical Datasets Via Probabilistic Programming

João Loula

Katherine M. Collins

Ulrich Schaechtle

Joshua B. Tenenbaum

Adrian Weller

Feras Saad

Timothy J. O'Donnell

Vikash Mansinghka

Accurate, efficient generative models of clinical populations could accelerate clinical research and improve patient outcomes. For example, … (see more)such models could infer probable treatment outcomes for different subpopulations, generate high-fidelity synthetic data that can be shared across organizational boundaries, and discover new relationships among clinical variables. Using Bayesian structure learning, we show that it is possible to learn probabilistic program models of clinical populations by combining data from multiple, sparsely overlapping clinical datasets. Through experiments with multiple clinical trials and real-world evidence from census health surveys, we show that our model generates higher quality synthetic data than neural network baselines, supports more accurate inferences across datasets than traditional statistical methods, and can be queried more efficiently than both, opening up new avenues for accessible and efficient AI assistance in clinical research.

2024-06-16

ICML.cc/2024/Workshop/AccMLBio (poster)

openreview.net

Lost in Translation: The Algorithmic Gap Between LMs and the Brain

Tosato Tommaso

Tikeng Notsawo Pascal Junior

Helbling Saskia

Irina Rish

Guillaume Dumas

Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing … (see more)in the brain remains unclear. This paper examines the gaps and overlaps between LMs and the brain at different levels of analysis, emphasizing the importance of looking beyond input-output behavior to examine and compare the internal processes of these systems. We discuss how insights from neuroscience, such as sparsity, modularity, internal states, and interactive learning, can inform the development of more biologically plausible language models. Furthermore, we explore the role of scaling laws in bridging the gap between LMs and human cognition, highlighting the need for efficiency constraints analogous to those in biological systems. By developing LMs that more closely mimic brain function, we aim to advance both artificial intelligence and our understanding of human cognition.

2024-06-16

ICML.cc/2024/Workshop/LLMs_and_Cognition (poster)

openreview.net

Neural Ratio Estimators Meet Distributional Shift and Mode Misspecification: A Cautionary Tale from Strong Gravitational Lensing

Andreas Filipp

Yashar Hezaveh

Laurence Perreault-Levasseur

In recent years, there has been increasing interest in the field of astrophysics in applying Neural Ratio Estimators (NREs) to large-scale i… (see more)nference problems where both amortization and marginalization over a large number of nuisance parameters are needed. Here, in order to assess the true potential of this method to produce unbiased inference on real data, we investigate the robustness of NREs to distribution shifts and model misspecification in the specific scientific application of the measurement of dark matter population-level parameters using strong gravitational lensing. We investigate the behaviour of a trained NRE for test data presenting distributional shifts inside the bounds of training, as well as out of distribution, both in the linear and non-linear parameters of this problem. While our results show that NREs perform when tested perfectly in distribution, we find that they exhibit significant biases and drawbacks when confronted with slight deviations from the examples seen in the training distribution. This indicates the necessity for caution when applying NREs to real astrophysical data, where underlying distributions are not perfectly known and models do not perfectly reconstruct the true underlying distributions.

2024-06-16

ICML.cc/2024/Workshop/SPIGM (poster)

openreview.net

On The Local Geometry of Deep Generative Manifolds

Ahmed Imtiaz Humayun

Candice Schumann

In this paper, we study theoretically inspired local geometric descriptors of the data manifolds approximated by pre-trained generative mode… (see more)ls. The descriptors – local scaling (ψ), local rank (ν), and local complexity (δ) — characterize the uncertainty, dimensionality, and smoothness on the learned manifold, using only the network weights and architecture. We investigate and emphasize their critical role in understanding generative models. Our analysis reveals that the local geometry is intricately linked to the quality and diversity of generated outputs. Additionally, we see that the geometric properties are distinct for out-of-distribution (OOD) inputs as well as for prompts memorized by Stable Diffusion, showing the possible application of our proposed descriptors for downstream detection and assessment of pre-trained generative models.

2024-06-16

ICML.cc/2024/Workshop/GRaM (published)

openreview.net

Expressivity of Neural Networks with Fixed Weights and Learned Biases

Ezekiel Williams

Avery Hee-Woon Ryoo

Thomas Jiralerspong

Alexandre Payeur

Matthew G Perich

Luca Mazzucato

Guillaume Lajoie

2024-06-15

ICML.cc/2024/Workshop/HiLD (poster)

openreview.net

Gradient descent induces alignment between weights and the pre-activation tangents for deep non-linear networks

Daniel Beaglehole

Ioannis Mitliagkas

Atish Agarwala

Understanding the mechanisms through which neural networks extract statistics from input-label pairs is one of the most important unsolved p… (see more)roblems in supervised learning. Prior works have identified that the gram matrices of the weights in trained neural networks of general architectures are proportional to the average gradient outer product of the model, in a statement known as the Neural Feature Ansatz (NFA). However, the reason these quantities become correlated during training is poorly understood. In this work, we clarify the nature of this correlation and explain its emergence at early training times. We identify that the NFA is equivalent to alignment between the left singular structure of the weight matrices and the newly defined pre-activation tangent kernel. We identify a centering of the NFA that isolates this alignment and is robust to initialization scale. We show that, through this centering, the speed of NFA development can be predicted analytically in terms of simple statistics of the inputs and labels.

2024-06-15

ICML.cc/2024/Workshop/HiLD (poster)

openreview.net

Gradient Dissent in Language Model Training and Saturation

Andrei Mircea

Ekaterina Lobacheva

Irina Rish

We seek to shed light on language model (LM) saturation from the perspective of learning dynamics. To this end, we define a decomposition o… (see more)f the cross-entropy gradient, which forms a shared low-dimensional basis for analyzing the training dynamics of models across scales. Intuitively, this decomposition consists of attractive and repulsive components that increase the logit of the correct class and decrease the logits of incorrect classes, respectively. Our analysis in this subspace reveals a phenomenon we term \textit{gradient dissent}, characterized by gradient components becoming systematically opposed such that loss cannot be improved along one component without being degraded along the other. Notably, we find that complete opposition, which we term \textit{total dissent}, reliably occurs in tandem with the saturation of smaller LMs. Based on these results, we hypothesize that gradient dissent can provide a useful foundation for better understanding and mitigating saturation.

2024-06-15

ICML.cc/2024/Workshop/HiLD (poster)

openreview.net

Inpainting Galaxy Counts onto N-Body Simulations over Multiple Cosmologies and Astrophysics

Matthew Ho

Laurence Perreault-Levasseur

2024-06-15

ICML.cc/2024/Workshop/AI4Science (poster)

openreview.net

Local lateral connectivity is sufficient for replicating cortex-like topographical organization in deep neural networks

Xinyu Qian

Amir Ozhan Dehghani

Asa Borzabadi Farahani

Pouya Bashivan

Across the primate cortex, neurons that perform similar functions tend to be spatially grouped together. This biological principle extends t… (see more)o many other species as well, reflecting a common way of organizing sensory processing across diverse forms of life. In the visual cortex, this biological principle manifests itself as a modular organization of neuronal clusters, each tuned to a specific visual property. The tendency toward short connections is widely believed to explain the existence of such an organization in the brains of many animals. However, the neural mechanisms underlying this phenomenon remain unclear. Here, we use artificial deep neural network models to demonstrate that a topographical organization akin to that in the primary, intermediate, and high-level human visual cortex emerges when units in these models are locally laterally connected and their weight parameters are tuned by top-down credit assignment. The emergence of modular organization without explicit topography-inducing learning rules or objective functions challenges their necessity and suggests that local lateral connectivity alone may suffice for the formation of topographic organization across the cortex. Furthermore, the incorporation of lateral connections in deep convolutional networks enhances their robustness to subtle alterations in visual inputs, such as those designed to deceive the model (i.e. adversarial examples), indicating an additional role for these connections in learning robust representations.

2024-06-15

ICML.cc/2024/Workshop/AI4Science (poster)

doi.org

openreview.net

Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology

Oren Kraus

Kian Kenyon-Dean

Saber Saberian

Maryam Fallah

Peter McLean

Jess Leung

Vasudev Sharma