MIT CSAIL
Abstract:Class imbalance remains a significant challenge in machine learning, particularly for tabular data classification tasks. While Gradient Boosting Decision Trees (GBDT) models have proven highly effective for such tasks, their performance can be compromised when dealing with imbalanced datasets. This paper presents the first comprehensive study on adapting class-balanced loss functions to three GBDT algorithms across various tabular classification tasks, including binary, multi-class, and multi-label classification. We conduct extensive experiments on multiple datasets to evaluate the impact of class-balanced losses on different GBDT models, establishing a valuable benchmark. Our results demonstrate the potential of class-balanced loss functions to enhance GBDT performance on imbalanced datasets, offering a robust approach for practitioners facing class imbalance challenges in real-world applications. Additionally, we introduce a Python package that facilitates the integration of class-balanced loss functions into GBDT workflows, making these advanced techniques accessible to a wider audience.
Abstract:The high resource consumption of large-scale models discourages resource-constrained users from developing their customized transformers. To this end, this paper considers a federated framework named Fed-Grow for multiple participants to cooperatively scale a transformer from their pre-trained small models. Under the Fed-Grow, a Dual-LiGO (Dual Linear Growth Operator) architecture is designed to help participants expand their pre-trained small models to a transformer. In Dual-LiGO, the Local-LiGO part is used to address the heterogeneity problem caused by the various pre-trained models, and the Global-LiGO part is shared to exchange the implicit knowledge from the pre-trained models, local data, and training process of participants. Instead of model sharing, only sharing the Global-LiGO strengthens the privacy of our approach. Compared with several state-of-the-art methods in simulation, our approach has higher accuracy, better precision, and lower resource consumption on computations and communications. To the best of our knowledge, most of the previous model-scaling works are centralized, and our work is the first one that cooperatively grows a transformer from multiple pre-trained heterogeneous models with the user privacy protected in terms of local data and models. We hope that our approach can extend the transformers to the broadly distributed scenarios and encourage more resource-constrained users to enjoy the bonus taken by the large-scale transformers.
Abstract:Cognitive Language Processing (CLP), situated at the intersection of Natural Language Processing (NLP) and cognitive science, plays a progressively pivotal role in the domains of artificial intelligence, cognitive intelligence, and brain science. Among the essential areas of investigation in CLP, Cognitive Signal Decoding (CSD) has made remarkable achievements, yet there still exist challenges related to insufficient global dynamic representation capability and deficiencies in multi-domain feature integration. In this paper, we introduce a novel paradigm for CLP referred to as Disentangled Frequency-Spatial-Temporal Attention(D-FaST). Specifically, we present an novel cognitive signal decoder that operates on disentangled frequency-space-time domain attention. This decoder encompasses three key components: frequency domain feature extraction employing multi-view attention, spatial domain feature extraction utilizing dynamic brain connection graph attention, and temporal feature extraction relying on local time sliding window attention. These components are integrated within a novel disentangled framework. Additionally, to encourage advancements in this field, we have created a new CLP dataset, MNRED. Subsequently, we conducted an extensive series of experiments, evaluating D-FaST's performance on MNRED, as well as on publicly available datasets including ZuCo, BCIC IV-2A, and BCIC IV-2B. Our experimental results demonstrate that D-FaST outperforms existing methods significantly on both our datasets and traditional CSD datasets including establishing a state-of-the-art accuracy score 78.72% on MNRED, pushing the accuracy score on ZuCo to 78.35%, accuracy score on BCIC IV-2A to 74.85% and accuracy score on BCIC IV-2B to 76.81%.
Abstract:Code generation with Large Language Models (LLMs) has been extensively studied and achieved remarkable progress. As a complementary aspect to code generation, test case generation is of crucial importance in ensuring the quality and reliability of code. However, using LLMs as test case generators has been much less explored. Current research along this line primarily focuses on enhancing code generation with assistance from test cases generated by LLMs, while the performance of LLMs in test case generation alone has not been comprehensively examined. To bridge this gap, we conduct extensive experiments to study how well LLMs can generate high-quality test cases. We find that as the problem difficulty increases, state-of-the-art LLMs struggle to generate correct test cases, largely due to their inherent limitations in computation and reasoning. To mitigate this issue, we further propose a multi-agent framework called \emph{TestChain} that decouples the generation of test inputs and test outputs. Notably, TestChain uses a ReAct format conversation chain for LLMs to interact with a Python interpreter in order to provide more accurate test outputs. Our results indicate that TestChain outperforms the baseline by a large margin. Particularly, in terms of the accuracy of test cases, TestChain using GPT-4 as the backbone achieves a 13.84\% improvement over the baseline on the LeetCode-hard dataset.
Abstract:Masked autoencoder (MAE) shows that severe augmentation during training produces robust representations for high-level tasks. This paper brings the MAE-like framework to nighttime image enhancement, demonstrating that severe augmentation during training produces strong network priors that are resilient to real-world night haze degradations. We propose a novel nighttime image dehazing method with self-prior learning. Our main novelty lies in the design of severe augmentation, which allows our model to learn robust priors. Unlike MAE that uses masking, we leverage two key challenging factors of nighttime images as augmentation: light effects and noise. During training, we intentionally degrade clear images by blending them with light effects as well as by adding noise, and subsequently restore the clear images. This enables our model to learn clear background priors. By increasing the noise values to approach as high as the pixel intensity values of the glow and light effect blended images, our augmentation becomes severe, resulting in stronger priors. While our self-prior learning is considerably effective in suppressing glow and revealing details of background scenes, in some cases, there are still some undesired artifacts that remain, particularly in the forms of over-suppression. To address these artifacts, we propose a self-refinement module based on the semi-supervised teacher-student framework. Our NightHaze, especially our MAE-like self-prior learning, shows that models trained with severe augmentation effectively improve the visibility of input haze images, approaching the clarity of clear nighttime images. Extensive experiments demonstrate that our NightHaze achieves state-of-the-art performance, outperforming existing nighttime image dehazing methods by a substantial margin of 15.5% for MUSIQ and 23.5% for ClipIQA.
Abstract:Integrated sensing and communication (ISAC) is a promising technology for 6G, with the goal of providing end-to-end information processing and inherent perception capabilities for future communication systems. Within ISAC emerging application scenarios, vehicular ISAC technologies have the potential to enhance traffic efficiency and safety through integration of communication and synchronized perception abilities. To establish a foundational theoretical support for vehicular ISAC system design and standardization, it is necessary to conduct channel measurements, and modeling to obtain a deep understanding of the radio propagation. In this paper, a dynamic statistical channel model is proposed for vehicular ISAC scenarios, incorporating Sensing Multipath Components (S-MPCs) and Clutter Multipath Components (C-MPCs), which are identified by the proposed tracking algorithm. Based on actual vehicular ISAC channel measurements at 28 GHz, time-varying sensing characteristics in front, left, and right directions are investigated. To model the dynamic evolution process of channel, number of new S-MPCs, lifetimes, initial power and delay positions, dynamic variations within their lifetimes, clustering, power decay, and fading of C-MPCs are statistically characterized. Finally, the paper provides implementation of dynamic vehicular ISAC model and validates it by comparing key simulation statistics between measurements and simulations.
Abstract:Recently, deep learning enabled semantic communications have been developed to understand transmission content from semantic level, which realize effective and accurate information transfer. Aiming to the vision of sixth generation (6G) networks, wireless devices are expected to have native perception and intelligent capabilities, which associate wireless channel with surrounding environments from physical propagation dimension to semantic information dimension. Inspired by these, we aim to provide a new paradigm on wireless channel from semantic level. A channel semantic model and its characterization framework are proposed in this paper. Specifically, a channel semantic model composes of status semantics, behavior semantics and event semantics. Based on actual channel measurement at 28 GHz, as well as multi-mode data, example results of channel semantic characterization are provided and analyzed, which exhibits reasonable and interpretable semantic information.
Abstract:Spatio-temporal graph (STG) learning is foundational for smart city applications, yet it is often hindered by data scarcity in many cities and regions. To bridge this gap, we propose a novel generative pre-training framework, GPDiff, for STG transfer learning. Unlike conventional approaches that heavily rely on common feature extraction or intricate transfer learning designs, our solution takes a novel approach by performing generative pre-training on a collection of model parameters optimized with data from source cities. We recast STG transfer learning as pre-training a generative hypernetwork, which generates tailored model parameters guided by prompts, allowing for adaptability to diverse data distributions and city-specific characteristics. GPDiff employs a diffusion model with a transformer-based denoising network, which is model-agnostic to integrate with powerful STG models. By addressing challenges arising from data gaps and the complexity of generalizing knowledge across cities, our framework consistently outperforms state-of-the-art baselines on multiple real-world datasets for tasks such as traffic speed prediction and crowd flow prediction. The implementation of our approach is available: https://github.com/PLUTO-SCY/GPDiff.
Abstract:Urban spatio-temporal prediction is crucial for informed decision-making, such as transportation management, resource optimization, and urban planning. Although pretrained foundation models for natural languages have experienced remarkable breakthroughs, wherein one general-purpose model can tackle multiple tasks across various domains, urban spatio-temporal modeling lags behind. Existing approaches for urban prediction are usually tailored for specific spatio-temporal scenarios, requiring task-specific model designs and extensive in-domain training data. In this work, we propose a universal model, UniST, for urban spatio-temporal prediction. Drawing inspiration from large language models, UniST achieves success through: (i) flexibility towards diverse spatio-temporal data characteristics, (ii) effective generative pre-training with elaborated masking strategies to capture complex spatio-temporal relationships, (iii) spatio-temporal knowledge-guided prompts that align and leverage intrinsic and shared knowledge across scenarios. These designs together unlock the potential of a one-for-all model for spatio-temporal prediction with powerful generalization capability. Extensive experiments on 15 cities and 6 domains demonstrate the universality of UniST in advancing state-of-the-art prediction performance, especially in few-shot and zero-shot scenarios.
Abstract:Social networks influence behaviors, preferences, and relationships and play a crucial role in the dissemination of information and norms within human societies. As large language models (LLMs) increasingly integrate into social and professional environments, understanding their behavior within the context of social networks and interactions becomes essential. Our study analyzes the behaviors of standard network structures and real-world networks to determine whether the dynamics of multiple LLMs align with human social dynamics. We explore various social network principles, including micro-level concepts such as preferential attachment, triadic closure, and homophily, as well as macro-level concepts like community structure and the small-world phenomenon. Our findings suggest that LLMs demonstrate all these principles when they are provided with network structures and asked about their preferences regarding network formation. Furthermore, we investigate LLMs' decision-making based on real-world networks to compare the strengths of these principles. Our results reveal that triadic closure and homophily have a stronger influence than preferential attachment and that LLMs substantially exceed random guessing in the task of network formation predictions. Overall, our study contributes to the development of socially aware LLMs by shedding light on LLMs' network formation behaviors and exploring their impacts on social dynamics and norms.