The Multimodal Learning for Earth and Environment Workshop (MultiEarth 2023) is the second annual CVPR workshop aimed at the monitoring and analysis of the health of Earth ecosystems by leveraging the vast amount of remote sensing data that is continuously being collected. The primary objective of this workshop is to bring together the Earth and environmental science communities as well as the multimodal representation learning communities to explore new ways of harnessing technological advancements in support of environmental monitoring. The MultiEarth Workshop also seeks to provide a common benchmark for processing multimodal remote sensing information by organizing public challenges focused on monitoring the Amazon rainforest. These challenges include estimating deforestation, detecting forest fires, translating synthetic aperture radar (SAR) images to the visible domain, and projecting environmental trends. This paper presents the challenge guidelines, datasets, and evaluation metrics. Our challenge website is available at https://sites.google.com/view/rainforest-challenge/multiearth-2023.

Traditional text classification typically categorizes texts into pre-defined coarse-grained classes, from which the produced models cannot handle the real-world scenario where finer categories emerge periodically for accurate services. In this work, we investigate the setting where fine-grained classification is done only using the annotation of coarse-grained categories and the coarse-to-fine mapping. We propose a lightweight contrastive clustering-based bootstrapping method to iteratively refine the labels of passages. During clustering, it pulls away negative passage-prototype pairs under the guidance of the mapping from both global and local perspectives. Experiments on NYT and 20News show that our method outperforms the state-of-the-art methods by a large margin.

In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: the emergence of new task-relevant information during learning from both modalities that was not present in either alone. We study this challenge of interaction quantification in a semi-supervised setting with only labeled unimodal data and naturally co-occurring multimodal data (e.g., unlabeled images and captions, video and corresponding audio) but when labeling them is time-consuming. Using a precise information-theoretic definition of interactions, our key contributions are the derivations of lower and upper bounds to quantify the amount of multimodal interactions in this semi-supervised setting. We propose two lower bounds based on the amount of shared information between modalities and the disagreement between separately trained unimodal classifiers, and derive an upper bound through connections to approximate algorithms for min-entropy couplings. We validate these estimated bounds and show how they accurately track true interactions. Finally, two semi-supervised multimodal applications are explored based on these theoretical results: (1) analyzing the relationship between multimodal performance and estimated interactions, and (2) self-supervised learning that embraces disagreement between modalities beyond agreement as is typically done.

Psycholinguistic analyses provide a means of evaluating large language model (LLM) output and making systematic comparisons to human-generated text. These methods can be used to characterize the psycholinguistic properties of LLM output and illustrate areas where LLMs fall short in comparison to human-generated text. In this work, we apply psycholinguistic methods to evaluate individual sentences from long-form analogies about biochemical concepts. We compare analogies generated by human subjects enrolled in introductory biochemistry courses to analogies generated by chatGPT. We perform a supervised classification analysis using 78 features extracted from Coh-metrix that analyze text cohesion, language, and readability (Graesser et. al., 2004). Results illustrate high performance for classifying student-generated and chatGPT-generated analogies. To evaluate which features contribute most to model performance, we use a hierarchical clustering approach. Results from this analysis illustrate several linguistic differences between the two sources.

Exploratory data analysis (EDA) is a vital procedure for data science projects. In this work, we introduce a stable equilibrium point (SEP) - based framework for improving the efficiency and solution quality of EDA. By exploiting the SEPs to be the representative points, our approach aims to generate high-quality clustering and data visualization for large-scale data sets. A very unique property of the proposed method is that the SEPs will directly encode the clustering properties of data sets. Compared with prior state-of-the-art clustering and data visualization methods, the proposed methods allow substantially improving computing efficiency and solution quality for large-scale data analysis tasks.

The Blackboard Architecture provides a mechanism for storing data and logic and using it to make decisions that impact the application environment that the Blackboard Architecture network models. While rule-fact-action networks can represent numerous types of data, the relationships that can be easily modeled are limited by the propositional logic nature of the rule-fact network structure. This paper proposes and evaluates the inclusion of containers and links in the Blackboard Architecture. These objects are designed to allow them to model organizational, physical, spatial and other relationships that cannot be readily or efficiently implemented as Boolean logic rules. Containers group related facts together and can be nested to implement complex relationships. Links interconnect containers that have a relationship that is relevant to their organizational purpose. Both objects, together, facilitate new ways of using the Blackboard Architecture and enable or simply its use for complex tasks that have multiple types of relationships that need to be considered during operations.

The Blackboard Architecture provides a mechanism for embodying data, decision making and actuation. Its versatility has been demonstrated across a wide number of application areas. However, it lacks the capability to directly model organizational, spatial and other relationships which may be useful in decision-making, in addition to the propositional logic embodied in the rule-fact-action network. Previous work has proposed the use of container objects and links as a mechanism to simultaneously model these organizational and other relationships, while leaving the operational logic modeled in the rules, facts and actions. While containers facilitate this modeling, their utility is limited by the need to manually define them. For systems which may have multiple instances of a particular type of object and which may build their network autonomously, based on sensing, the reuse of logical structures facilitates operations and reduces storage and processing needs. This paper, thus, presents and assesses two additional concepts to add to the Blackboard Architecture: common properties and generic rules. Common properties are facts associated with containers which are defined as representing the same information across the various objects that they are associated with. Generic rules provide logical propositions that use these generic rules across links and apply to any objects matching their definition. The potential uses of these two new concepts are discussed herein and their impact on system performance is characterized.

The statement is a relatively short have a broad and significant impact on financial market document of about two pages that summarizes current trends, pricing of risky assets, and spillover to the real economic perceptions, the monetary policy determined, economy, market participants are trying to better and the names of the voters. The transcripts of the press understand the changes in the future monetary policy conference consist of a transcript to be read by the outlook of central banks. In particular, the monetary policy chairperson at the beginning of the conference, as well as of the Central Bank of the United States (Federal Reserve questions and answers with reporters, and are System, hereinafter Fed) is positioned as the most approximately 20 ~ 30 pages in volume. In some cases, important because it influences the movement of the dollar, information that is not included in the statement but is of the key currency. One of the means by which central banks interest to market participants (specific information and engage in dialogue with the market and conduct smooth future prospects) is recorded. The minutes are a document policy management is the publication of various that confirms the content of the economic analysis documents, including statements and minutes issued after reported by the Fed economists, the process of discussion policy meetings, and transcripts of speeches and that led to the decision of the policy, and the variation of congressional testimony attended by senior officials. The opinion among the members, and the volume is around Federal Open Market Committee (FOMC), a meeting at 10~20 pages. Outside of the FOMC meetings, transcripts which U.S. monetary policy is formulated, meets eight of speeches and interviews by FOMC participants (Fed times a year with members of the Federal Reserve Board officials) and statements in congressional testimony will (FRB) and the presidents of the regional Fed banks as be released at each meeting.

Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. However, such internalized knowledge might be insufficient and incorrect, which could lead LLMs to generate factually wrong answers. Furthermore, fine-tuning LLMs to update their knowledge is expensive. To this end, we propose to augment the knowledge directly in the input of LLMs. Specifically, we first retrieve the relevant facts to the input question from the knowledge graph based on semantic similarities between the question and its associated facts. After that, we prepend the retrieved facts to the input question in the form of the prompt, which is then forwarded to LLMs to generate the answer. Our framework, Knowledge-Augmented language model PromptING (KAPING), requires no model training, thus completely zero-shot. We validate the performance of our KAPING framework on the knowledge graph question answering task, that aims to answer the user's question based on facts over a knowledge graph, on which ours outperforms relevant zero-shot baselines by up to 48% in average, across multiple LLMs of various sizes.

Integrating ethical practices into the AI development process for artificial intelligence (AI) is essential to ensure safe, fair, and responsible operation. AI ethics involves applying ethical principles to the entire life cycle of AI systems. This is essential to mitigate potential risks and harms associated with AI, such as algorithm biases. To achieve this goal, responsible design patterns (RDPs) are critical for Machine Learning (ML) pipelines to guarantee ethical and fair outcomes. In this paper, we propose a comprehensive framework incorporating RDPs into ML pipelines to mitigate risks and ensure the ethical development of AI systems. Our framework comprises new responsible AI design patterns for ML pipelines identified through a survey of AI ethics and data management experts and validated through real-world scenarios with expert feedback. The framework guides AI developers, data scientists, and policy-makers to implement ethical practices in AI development and deploy responsible AI systems in production.