{"paper_id":"2309.01363","title":"Mutual information maximizing quantum generative adversarial networks","authors":["Mingyu Lee","Myeongjin Shin","Junseo Lee","Kabgyun Jeong"],"paper_date":"2023-09-04","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2309.01363v2","page_url":"https://thequant.space/flowcharts/mutual-information-maximizing-quantum-generative-adversarial/","scores":{"empirical_rigor":2,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes InfoQGAN, a quantum‑classical hybrid generative adversarial network that combines a variational quantum generator, a classical discriminator, and a Mutual Information Neural Estimator (MINE) to maximize mutual information between latent codes and generated samples.","quote":"To overcome these limitations, we propose InfoQGAN, a novel quantum-classical hybrid generative adversarial network that integrates the principles of InfoGAN with a QGAN architecture. Our approach employs a variational quantum circuit for data generation, a classical discriminator, and a Mutual Information Neural Estimator (MINE) to explicitly optimize the mutual information between latent codes and generated","summary":"One of the most promising applications in the era of Noisy Intermediate-Scale Quantum (NISQ) computing is quantum generative adversarial networks (QGANs), which offer significant quantum advantages over classical machine learning in various domains. However, QGANs suffer from mode collapse and lack…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Training and evaluation are performed on an ideal quantum simulator (and optionally a noisy Qiskit GenericBackendV2 simulator).","type":"model","stated":"implied","quote":"2-dimensional data generation All training was conducted on an ideal simulator, and for InfoQGAN and QGAN, we also compared results obtained using the Qiskit GenericBackendV2 simulator (hereafter referred to as the noisy environment).","support":"full"},{"assumption":"The quantum generator architecture (number of qubits, layers, and parameters) is identical for InfoQGAN and the baseline QGAN.","type":"model","stated":"explicit","quote":"To ensure a fair comparison, the generators in InfoQGAN and QGAN share the same architecture 3/11 and number of parameters. The generator circuit structure is identical for both InfoQGAN and QGAN.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Synthetic 2‑dimensional uniform diamond‑shaped distribution","provider":null,"kind":"synthetic","access":"public","period":null,"universe":null,"quote":"The predefined target 2D distribution is a uniform, diamond-shaped region within the [0,1] domain, centered at (0.6,0.6) with a side length of 0.4. We used a quantum generator with 5 qubits and 10 layers, resulting in 50 trainable parameters.","support":"full"},{"name":"Extended IRIS dataset","provider":null,"kind":"benchmark","access":"public","period":null,"universe":"150 original samples, extended to 1,200 samples","quote":"Iris dataset augmentation The IRIS dataset was first introduced in a seminal paper by R.A. Fisher26. To address this, we used the extended IRIS dataset29, which includes additional dimensions and comprises 1,200 samples.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"InfoQGAN significantly mitigates mode collapse compared to QGAN, as evidenced by more diverse generated samples and improved training stability.","kind":"performance","quote":"In the outputs generated by QGAN across different epochs, samples tend to cluster in specific regions, suggesting that the model captures only a subset of the target distribution. Furthermore, the model frequently oscillates between these modes, leading to reduced training stability.","support":"full"},{"finding":"InfoQGAN achieves robust feature disentanglement, enabling controlled generation of arbitrary target distributions that QGAN cannot produce.","kind":"performance","quote":"As you can see, InfoQGAN could generate the arbitrary distributions we designed, but this was not possible in QGAN because the latent code has no meaning. This approach works because InfoQGAN does not cause mode collapse and allows for feature disentanglement.","support":"full"},{"finding":"When used for data augmentation on the IRIS dataset, InfoQGAN improves classification accuracy by 1.43, 2.00, and 2.88 percentage points for Decision Tree, Logistic Regression, and k‑Nearest Neighbors respectively.","kind":"performance","quote":"Augmenting the dataset with InfoQGAN led to performance improvements of 1.43pp, 2.00pp, and 2.88pp across the three classification models.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/red1108/InfoQGAN","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T20:01:20Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}