Multimodal fusion of multiple heterogeneous and interconnected signals is a fundamental challenge in almost all multimodal problems and applications. In order to perform multimodal fusion, we need to understand the types of interactions that modalities can exhibit: how each modality individually provides information useful for a task and how this information changes in the presence of other modalities. In this paper, we perform a comparative study of how human annotators can be leveraged to annotate two categorizations of multimodal interactions: (1) partial labels, where different randomly assigned annotators annotate the label given the first, second, and both modalities, and (2) counterfactual labels, where the same annotator is tasked to annotate the label given the first modality before giving them the second modality and asking them to explicitly reason about how their answer changes, before proposing an alternative taxonomy based on (3) information decomposition, where annotators annotate the degrees of redundancy: the extent to which modalities individually and together give the same predictions on the task, uniqueness: the extent to which one modality enables a task prediction that the other does not, and synergy: the extent to which only both modalities enable one to make a prediction about the task that one would not otherwise make using either modality individually. Through extensive experiments and annotations, we highlight several opportunities and limitations of each approach and propose a method to automatically convert annotations of partial and counterfactual labels to information decomposition, yielding an accurate and efficient method for quantifying interactions in multimodal datasets.
Self-supervised learning (SSL) and the objective of masking-and-predicting in particular have led to promising SSL performance on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition from the field of education that deciding what to mask can substantially improve learning outcomes. We introduce Difference-Masking, an approach that automatically chooses what to mask during continued pretraining by considering what makes an unlabelled target domain different from the pretraining domain. Empirically, we find that Difference-Masking outperforms baselines on continued pretraining settings across four diverse language and multimodal video tasks. The cross-task applicability of Difference-Masking supports the effectiveness of our framework for SSL pretraining in language, vision, and other domains.
Accurately modeling affect dynamics, which refers to the changes and fluctuations in emotions and affective displays during human conversations, is crucial for understanding human interactions. By analyzing affect dynamics, we can gain insights into how people communicate, respond to different situations, and form relationships. However, modeling affect dynamics is challenging due to contextual factors, such as the complex and nuanced nature of interpersonal relationships, the situation, and other factors that influence affective displays. To address this challenge, we propose a Cross-person Memory Transformer (CPM-T) framework which is able to explicitly model affective dynamics (intrapersonal and interpersonal influences) by identifying verbal and non-verbal cues, and with a large language model to utilize the pre-trained knowledge and perform verbal reasoning. The CPM-T framework maintains memory modules to store and update the contexts within the conversation window, enabling the model to capture dependencies between earlier and later parts of a conversation. Additionally, our framework employs cross-modal attention to effectively align information from multi-modalities and leverage cross-person attention to align behaviors in multi-party interactions. We evaluate the effectiveness and generalizability of our approach on three publicly available datasets for joint engagement, rapport, and human beliefs prediction tasks. Remarkably, the CPM-T framework outperforms baseline models in average F1-scores by up to 7.3%, 9.3%, and 2.0% respectively. Finally, we demonstrate the importance of each component in the framework via ablation studies with respect to multimodal temporal behavior.
The recent explosion of interest in multimodal applications has resulted in a wide selection of datasets and methods for representing and integrating information from different signals. Despite these empirical advances, there remain fundamental research questions: how can we quantify the nature of interactions that exist among input features? Subsequently, how can we capture these interactions using suitable data-driven methods? To answer this question, we propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy across input features, which we term the PID statistics of a multimodal distribution. Using 2 newly proposed estimators that scale to high-dimensional distributions, we demonstrate their usefulness in quantifying the interactions within multimodal datasets, the nature of interactions captured by multimodal models, and principled approaches for model selection. We conduct extensive experiments on both synthetic datasets where the PID statistics are known and on large-scale multimodal benchmarks where PID estimation was previously impossible. Finally, to demonstrate the real-world applicability of our approach, we present three case studies in pathology, mood prediction, and robotic perception where our framework accurately recommends strong multimodal models for each application.
High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-performing agent. We propose the Read and Reward framework. Read and Reward speeds up RL algorithms on Atari games by reading manuals released by the Atari game developers. Our framework consists of a QA Extraction module that extracts and summarizes relevant information from the manual and a Reasoning module that evaluates object-agent interactions based on information from the manual. Auxiliary reward is then provided to a standard A2C RL agent, when interaction is detected. When assisted by our design, A2C improves on 4 games in the Atari environment with sparse rewards, and requires 1000x less training frames compared to the previous SOTA Agent 57 on Skiing, the hardest game in Atari.
Despite recent progress towards scaling up multimodal vision-language models, these models are still known to struggle on compositional generalization benchmarks such as Winoground. We find that a critical component lacking from current vision-language models is relation-level alignment: the ability to match directional semantic relations in text (e.g., "mug in grass") with spatial relationships in the image (e.g., the position of the mug relative to the grass). To tackle this problem, we show that relation alignment can be enforced by encouraging the directed language attention from 'mug' to 'grass' (capturing the semantic relation 'in') to match the directed visual attention from the mug to the grass. Tokens and their corresponding objects are softly identified using the cross-modal attention. We prove that this notion of soft relation alignment is equivalent to enforcing congruence between vision and language attention matrices under a 'change of basis' provided by the cross-modal attention matrix. Intuitively, our approach projects visual attention into the language attention space to calculate its divergence from the actual language attention, and vice versa. We apply our Cross-modal Attention Congruence Regularization (CACR) loss to UNITER and improve on the state-of-the-art approach to Winoground.
Pretrained language models have demonstrated extraordinary capabilities in language generation. However, real-world tasks often require controlling the distribution of generated text in order to mitigate bias, promote fairness, and achieve personalization. Existing techniques for controlling the distribution of generated text only work with quantified distributions, which require pre-defined categories, proportions of the distribution, or an existing corpus following the desired distributions. However, many important distributions, such as personal preferences, are unquantified. In this work, we tackle the problem of generating text following arbitrary distributions (quantified and unquantified) by proposing Nano, a few-shot human-in-the-loop training algorithm that continuously learns from human feedback. Nano achieves state-of-the-art results on single topic/attribute as well as quantified distribution control compared to previous works. We also show that Nano is able to learn unquantified distributions, achieves personalization, and captures differences between different individuals' personal preferences with high sample efficiency.
Pre-trained language models (PLMs) have gained increasing popularity due to their compelling prediction performance in diverse natural language processing (NLP) tasks. When formulating a PLM-based prediction pipeline for NLP tasks, it is also crucial for the pipeline to minimize the calibration error, especially in safety-critical applications. That is, the pipeline should reliably indicate when we can trust its predictions. In particular, there are various considerations behind the pipeline: (1) the choice and (2) the size of PLM, (3) the choice of uncertainty quantifier, (4) the choice of fine-tuning loss, and many more. Although prior work has looked into some of these considerations, they usually draw conclusions based on a limited scope of empirical studies. There still lacks a holistic analysis on how to compose a well-calibrated PLM-based prediction pipeline. To fill this void, we compare a wide range of popular options for each consideration based on three prevalent NLP classification tasks and the setting of domain shift. In response, we recommend the following: (1) use ELECTRA for PLM encoding, (2) use larger PLMs if possible, (3) use Temp Scaling as the uncertainty quantifier, and (4) use Focal Loss for fine-tuning.
Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design computer agents with intelligent capabilities such as understanding, reasoning, and learning through integrating multiple communicative modalities, including linguistic, acoustic, visual, tactile, and physiological messages. With the recent interest in video understanding, embodied autonomous agents, text-to-image generation, and multisensor fusion in application domains such as healthcare and robotics, multimodal machine learning has brought unique computational and theoretical challenges to the machine learning community given the heterogeneity of data sources and the interconnections often found between modalities. However, the breadth of progress in multimodal research has made it difficult to identify the common themes and open questions in the field. By synthesizing a broad range of application domains and theoretical frameworks from both historical and recent perspectives, this paper is designed to provide an overview of the computational and theoretical foundations of multimodal machine learning. We start by defining two key principles of modality heterogeneity and interconnections that have driven subsequent innovations, and propose a taxonomy of 6 core technical challenges: representation, alignment, reasoning, generation, transference, and quantification covering historical and recent trends. Recent technical achievements will be presented through the lens of this taxonomy, allowing researchers to understand the similarities and differences across new approaches. We end by motivating several open problems for future research as identified by our taxonomy.
Lecture slide presentations, a sequence of pages that contain text and figures accompanied by speech, are constructed and presented carefully in order to optimally transfer knowledge to students. Previous studies in multimedia and psychology attribute the effectiveness of lecture presentations to their multimodal nature. As a step toward developing AI to aid in student learning as intelligent teacher assistants, we introduce the Multimodal Lecture Presentations dataset as a large-scale benchmark testing the capabilities of machine learning models in multimodal understanding of educational content. Our dataset contains aligned slides and spoken language, for 180+ hours of video and 9000+ slides, with 10 lecturers from various subjects (e.g., computer science, dentistry, biology). We introduce two research tasks which are designed as stepping stones towards AI agents that can explain (automatically captioning a lecture presentation) and illustrate (synthesizing visual figures to accompany spoken explanations) educational content. We provide manual annotations to help implement these two research tasks and evaluate state-of-the-art models on them. Comparing baselines and human student performances, we find that current models struggle in (1) weak crossmodal alignment between slides and spoken text, (2) learning novel visual mediums, (3) technical language, and (4) long-range sequences. Towards addressing this issue, we also introduce PolyViLT, a multimodal transformer trained with a multi-instance learning loss that is more effective than current approaches. We conclude by shedding light on the challenges and opportunities in multimodal understanding of educational presentations.