Search

Existing music generation models are mostly language-based, neglecting the frequency continuity property of notes, resulting in inadequate fitting of rare or never-used notes and thus reducing the diversity of generated samples. We argue that the distribution of notes can be modeled by translational invariance and periodicity, especially using diffusion models to generalize notes by injecting frequency-domain Gaussian noise. However, due to the low-density nature of music symbols, estimating the distribution of notes latent in the high-density solution space poses significant challenges. To address this problem, we introduce the Music-Diff architecture, which fits a joint distribution of notes and accompanying semantic information to generate symbolic music conditionally. We first enhance the fragmentation module for extracting semantics by using event-based notations and the structural similarity index, thereby preventing boundary blurring. As a prerequisite for multivariate perturbation, we introduce a joint pre-training method to construct the progressions between notes and musical semantics while avoiding direct modeling of low-density notes. Finally, we recover the perturbed notes by a multi-branch denoiser that fits multiple noise objectives via Pareto optimization. Our experiments suggest that in contrast to language models, joint probability diffusion models perturbing at both note and semantic levels can provide more sample diversity and compositional regularity. The case study highlights the rhythmic advantages of our model over language- and DDPMs-based models by analyzing the hierarchical structure expressed in the self-similarity metrics.

As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benchmarks mainly focus on evaluating solely on task performance, such as the accuracy of identifying the attribute of an object. Combining well-developed cognitive science to understand the intelligence of MLLMs beyond superficial achievements remains largely unexplored. To this end, we introduce the first cognitive-driven multi-lingual and multi-modal benchmark to evaluate the general intelligence ability of MLLMs, dubbed M3GIA. Specifically, we identify five key cognitive factors based on the well-recognized Cattell-Horn-Carrol (CHC) model of intelligence and propose a novel evaluation metric. In addition, since most MLLMs are trained to perform in different languages, a natural question arises: is language a key factor influencing the cognitive ability of MLLMs? As such, we go beyond English to encompass other languages based on their popularity, including Chinese, French, Spanish, Portuguese and Korean, to construct our M3GIA. We make sure all the data relevant to the cultural backgrounds are collected from their native context to avoid English-centric bias. We collected a significant corpus of data from human participants, revealing that the most advanced MLLM reaches the lower boundary of human intelligence in English. Yet, there remains a pronounced disparity in the other five languages assessed. We also reveals an interesting winner takes all phenomenon that are aligned with the discovery in cognitive studies. Our benchmark will be open-sourced, with the aspiration of facilitating the enhancement of cognitive capabilities in MLLMs.

Graph neural networks (GNNs) have gained wide popularity in recommender systems due to their capability to capture higher-order structure information among the nodes of users and items. However, these methods need to collect personal interaction data between a user and the corresponding items and then model them in a central server, which would break the privacy laws such as GDPR. So far, no existing work can construct a global graph without leaking each user's private interaction data (i.e., his or her subgraph). In this paper, we are the first to design a novel lossless federated recommendation framework based on GNN, which achieves full-graph training with complete high-order structure information, enabling the training process to be equivalent to the corresponding un-federated counterpart. In addition, we use LightGCN to instantiate an example of our framework and show its equivalence.

Underwater acoustic target recognition (UATR) and localization (UATL) play important roles in marine exploration. The highly noisy acoustic signal and time-frequency interference among various sources pose big challenges to this task. To tackle these issues, we propose a multimodal approach to extract and fuse audio-visual-textual information to recognize and localize underwater targets through the designed Symbiotic Transformer (Symb-Trans) and Multi-View Regression (MVR) method. The multimodal data were first preprocessed by a custom-designed HetNorm module to normalize the multi-source data in a common feature space. The Symb-Trans module embeds audiovisual features by co-training the preprocessed multimodal features through parallel branches and a content encoder with cross-attention. The audiovisual features are then used for underwater target recognition. Meanwhile, the text embedding combined with the audiovisual features is fed to an MVR module to predict the localization of the underwater targets through multi-view clustering and multiple regression. Since no off-the-shell multimodal dataset is available for UATR and UATL, we combined multiple public datasets, consisting of acoustic, and/or visual, and/or textural data, to obtain audio-visual-textual triplets for model training and validation. Experiments show that our model outperforms comparative methods in 91.7% (11 out of 12 metrics) and 100% (4 metrics) of the quantitative metrics for the recognition and localization tasks, respectively. In a case study, we demonstrate the advantages of multi-view models in establishing sample discriminability through visualization methods. For UATL, the proposed MVR method produces the relation graphs, which allow predictions based on records of underwater targets with similar conditions.

Symbolic Music Generation relies on the contextual representation capabilities of the generative model, where the most prevalent approach is the Transformer-based model. The learning of musical context is also related to the structural elements in music, i.e. intro, verse, and chorus, which are currently overlooked by the research community. In this paper, we propose a hierarchical Transformer model to learn multi-scale contexts in music. In the encoding phase, we first designed a Fragment Scope Localization layer to syncopate the music into chords and sections. Then, we use a multi-scale attention mechanism to learn note-, chord-, and section-level contexts. In the decoding phase, we proposed a hierarchical Transformer model that uses fine-decoders to generate sections in parallel and a coarse-decoder to decode the combined music. We also designed a Music Style Normalization layer to achieve a consistent music style between the generated sections. Our model is evaluated on two open MIDI datasets, and experiments show that our model outperforms the best contemporary music generative models. More excitingly, the visual evaluation shows that our model is superior in melody reuse, resulting in more realistic music.

Opportunistic networks (OppNets) are modern types of intermittently connected networks in which mobile users communicate with each other via their short-range devices to share data among interested observers. In this setting, humans are the main carriers of mobile devices. As such, this mobility can be exploited by retrieving inherent user habits, interests, and social features for the simulation and evaluation of various scenarios. Several research challenges concerning human mobility in OppNets have been explored in the literature recently. In this paper, we present a thorough survey of human mobility issues in three main groups (1) mobility characteristics, (2) mobility models and traces, and (3) mobility prediction techniques. Firstly, spatial, temporal, and connectivity properties of human motion are explored. Secondly, real mobility traces which have been captured using Bluetooth/Wi-Fi technologies or location-based social networks are summarized. Furthermore, simulation-based mobility models are categorized and state-of-the art articles in each category are highlighted. Thirdly, new human mobility prediction techniques which aim to forecast the three aspects of human mobility, i.e., users' next walks, stay duration and contact opportunities are studied comparatively. To conclude, some major open issues are outlined., Comment: 18 pages, 1 figure