We address the growing apprehension that GNNs, in the absence of fairness constraints, might produce biased decisions that disproportionately affect underprivileged groups or individuals. Departing from previous work, we introduce for the first time a method for incorporating the Gini coefficient as a measure of fairness to be used within the GNN framework. Our proposal, GRAPHGINI, works with the two different goals of individual and group fairness in a single system, while maintaining high prediction accuracy. GRAPHGINI enforces individual fairness through learnable attention scores that help in aggregating more information through similar nodes. A heuristic-based maximum Nash social welfare constraint ensures the maximum possible group fairness. Both the individual fairness constraint and the group fairness constraint are stated in terms of a differentiable approximation of the Gini coefficient. This approximation is a contribution that is likely to be of interest even beyond the scope of the problem studied in this paper. Unlike other state-of-the-art, GRAPHGINI automatically balances all three optimization objectives (utility, individual, and group fairness) of the GNN and is free from any manual tuning of weight parameters. Extensive experimentation on real-world datasets showcases the efficacy of GRAPHGINI in making significant improvements in individual fairness compared to all currently available state-of-the-art methods while maintaining utility and group equality.
In spoken dialogue, even if two current turns are the same sentence, their responses might still differ when they are spoken in different styles. The spoken styles, containing paralinguistic and prosodic information, mark the most significant difference between text and speech modality. When using text-only LLMs to model spoken dialogue, text-only LLMs cannot give different responses based on the speaking style of the current turn. In this paper, we focus on enabling LLMs to listen to the speaking styles and respond properly. Our goal is to teach the LLM that "even if the sentences are identical if they are spoken in different styles, their corresponding responses might be different". Since there is no suitable dataset for achieving this goal, we collect a speech-to-speech dataset, StyleTalk, with the following desired characteristics: when two current speeches have the same content but are spoken in different styles, their responses will be different. To teach LLMs to understand and respond properly to the speaking styles, we propose the Spoken-LLM framework that can model the linguistic content and the speaking styles. We train Spoken-LLM using the StyleTalk dataset and devise a two-stage training pipeline to help the Spoken-LLM better learn the speaking styles. Based on extensive experiments, we show that Spoken-LLM outperforms text-only baselines and prior speech LLMs methods.
Video-Language Models (VLMs), powered by the advancements in Large Language Models (LLMs), are charting new frontiers in video understanding. A pivotal challenge is the development of an efficient method to encapsulate video content into a set of representative tokens to align with LLMs. In this work, we introduce Slot-VLM, a novel framework designed to generate semantically decomposed video tokens, in terms of object-wise and event-wise visual representations, to facilitate LLM inference. Particularly, we design a SlowFast Slots module, i.e., SF-Slots, that adaptively aggregates the dense video tokens from the CLIP vision encoder to a set of representative slots. In order to take into account both the spatial object details and the varied temporal dynamics, SF-Slots is built with a dual-branch structure. The Slow-Slots branch focuses on extracting object-centric slots from features at high spatial resolution but low (slow) frame sample rate, emphasizing detailed object information. Conversely, Fast-Slots branch is engineered to learn event-centric slots from high temporal sample rate but low spatial resolution features. These complementary slots are combined to form the vision context, serving as the input to the LLM for efficient question answering. Our experimental results demonstrate the effectiveness of our Slot-VLM, which achieves the state-of-the-art performance on video question-answering.
Applying DevOps practices to machine learning system is termed as MLOps and machine learning systems evolve on new data unlike traditional systems on requirements. The objective of MLOps is to establish a connection between different open-source tools to construct a pipeline that can automatically perform steps to construct a dataset, train the machine learning model and deploy the model to the production as well as store different versions of model and dataset. Benefits of MLOps is to make sure the fast delivery of the new trained models to the production to have accurate results. Furthermore, MLOps practice impacts the overall quality of the software products and is completely dependent on open-source tools and selection of relevant open-source tools is considered as challenged while a generalized method to select an appropriate open-source tools is desirable. In this paper, we present a framework for recommendation system that processes the contextual information (e.g., nature of data, type of the data) of the machine learning project and recommends a relevant toolchain (tech-stack) for the operationalization of machine learning systems. To check the applicability of the proposed framework, four different approaches i.e., rule-based, random forest, decision trees and k-nearest neighbors were investigated where precision, recall and f-score is measured, the random forest out classed other approaches with highest f-score value of 0.66.
The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by information loss and poor generalization ability, resulting in new PA materials and fingerprint sensors. This paper thus proposes a global-local model-based PAD (RTK-PAD) method to overcome those limitations to some extent. The proposed method consists of three modules, called: 1) the global module; 2) the local module; and 3) the rethinking module. By adopting the cut-out-based global module, a global spoofness score predicted from nonlocal features of the entire fingerprint images can be achieved. While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained. The two modules are not independent but connected through our proposed rethinking module by localizing two discriminative patches for the local module based on the global spoofness score. Finally, the fusion spoofness score by averaging the global and local spoofness scores is used for PAD. Our experimental results evaluated on LivDet 2017 show that the proposed RTK-PAD can achieve an average classification error (ACE) of 2.28% and a true detection rate (TDR) of 91.19% when the false detection rate (FDR) equals 1.0%, which significantly outperformed the state-of-the-art methods by $\sim$10% in terms of TDR (91.19% versus 80.74%).
In recent years, large language models have achieved significant success in generative tasks (e.g., speech cloning and audio generation) related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serves as an intermediate representation replacing the mel-spectrogram. However, there exist several gaps between discrete codecs and downstream speech language models. Specifically, 1) most codec models are trained on only 1,000 hours of data, whereas most speech language models are trained on 60,000 hours; 2) Achieving good reconstruction performance requires the utilization of numerous codebooks, which increases the burden on downstream speech language models; 3) The initial channel of the codebooks contains excessive information, making it challenging to directly generate acoustic tokens from weakly supervised signals such as text in downstream tasks. Consequently, leveraging the characteristics of speech language models, we propose Language-Codec. In the Language-Codec, we introduce a Mask Channel Residual Vector Quantization (MCRVQ) mechanism along with improved Fourier transform structures and larger training datasets to address the aforementioned gaps. We compare our method with competing audio compression algorithms and observe significant outperformance across extensive evaluations. Furthermore, we also validate the efficiency of the Language-Codec on downstream speech language models. The source code and pre-trained models can be accessed at https://github.com/jishengpeng/languagecodec .
Graphs data is crucial for many applications, and much of it exists in the relations described in textual format. As a result, being able to accurately recall and encode a graph described in earlier text is a basic yet pivotal ability that LLMs need to demonstrate if they are to perform reasoning tasks that involve graph-structured information. Human performance at graph recall has been studied by cognitive scientists for decades, and has been found to often exhibit certain structural patterns of bias that align with human handling of social relationships. To date, however, we know little about how LLMs behave in analogous graph recall tasks: do their recalled graphs also exhibit certain biased patterns, and if so, how do they compare with humans and affect other graph reasoning tasks? In this work, we perform the first systematical study of graph recall by LLMs, investigating the accuracy and biased microstructures (local structural patterns) in their recall. We find that LLMs not only underperform often in graph recall, but also tend to favor more triangles and alternating 2-paths. Moreover, we find that more advanced LLMs have a striking dependence on the domain that a real-world graph comes from -- by yielding the best recall accuracy when the graph is narrated in a language style consistent with its original domain.
Traveling waves are a fundamental phenomenon in the brain, playing a crucial role in short-term information storage. In this study, we leverage the concept of traveling wave dynamics within a neural lattice to formulate a theoretical model of neural working memory, study its properties, and its real world implications in AI. The proposed model diverges from traditional approaches, which assume information storage in static, register-like locations updated by interference. Instead, the model stores data as waves that is updated by the wave's boundary conditions. We rigorously examine the model's capabilities in representing and learning state histories, which are vital for learning history-dependent dynamical systems. The findings reveal that the model reliably stores external information and enhances the learning process by addressing the diminishing gradient problem. To understand the model's real-world applicability, we explore two cases: linear boundary condition and non-linear, self-attention-driven boundary condition. The experiments reveal that the linear scenario is effectively learned by Recurrent Neural Networks (RNNs) through backpropagation when modeling history-dependent dynamical systems. Conversely, the non-linear scenario parallels the autoregressive loop of an attention-only transformer. Collectively, our findings suggest the broader relevance of traveling waves in AI and its potential in advancing neural network architectures.
The wide availability of specific courses together with the flexibility of academic plans in university studies reveal the importance of Recommendation Systems (RSs) in this area. These systems appear as tools that help students to choose courses that suit to their personal interests and their academic performance. This paper presents a hybrid RS that combines Collaborative Filtering (CF) and Content-based Filtering (CBF) using multiple criteria related both to student and course information to recommend the most suitable courses to the students. A Genetic Algorithm (GA) has been developed to automatically discover the optimal RS configuration which include both the most relevant criteria and the configuration of the rest of parameters. The experimental study has used real information of Computer Science Degree of University of Cordoba (Spain) including information gathered from students during three academic years, counting on 2500 entries of 95 students and 63 courses. Experimental results show a study of the most relevant criteria for the course recommendation, the importance of using a hybrid model that combines both student information and course information to increase the reliability of the recommendations as well as an excellent performance compared to previous models.
The theory of sampling and recovery of bandlimited graph signals has been extensively studied. However, in many cases, the observation of a signal is quite coarse. For example, users only provide simple comments such as "like" or "dislike" for a product on an e-commerce platform. This is a particular scenario where only the sign information of a graph signal can be measured. In this paper, we are interested in how to sample based on sign information in an online manner, by which the direction of the original graph signal can be estimated. The online signed sampling problem of a graph signal can be formulated as a Markov decision process in a finite horizon. Unfortunately, it is intractable for large size graphs. We propose a low-complexity greedy signed sampling algorithm (GSS) as well as a stopping criterion. Meanwhile, we prove that the objective function is adaptive monotonic and adaptive submodular, so that the performance is close enough to the global optimum with a lower bound. Finally, we demonstrate the effectiveness of the GSS algorithm by both synthesis and realworld data.